{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/hallucination/papers/ran/2","list_of":"/task/hallucination","task":"Hallucination","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":276,"counts":{"archive_papers_tagged":1816,"with_a_code_link":752,"where_syntology_ran_a_sample":276,"not_listed_spam_title":0,"listed":1816,"listed_where_code_ran":276,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":240,"every_run_a_failure_of_syntologys_instrument":36,"listed_with_a_run_with_no_instrument_failure":240,"listed_every_run_a_failure_of_syntologys_instrument":36,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/hallucination/papers/ran/1","prev":"/task/hallucination/papers/ran/1","next":"/task/hallucination/papers/ran/3","papers":[{"url":"/paper/knowledge-graph-enhanced-large-language","slug":"knowledge-graph-enhanced-large-language","title":"Knowledge Graph-Enhanced Large Language Models via Path Selection","date":"2024-06-19","arxiv_id":"2406.13862","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/knowledge-graph-enhanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.13862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13862"}},"official":{"repos":["haochenliu2000/kelp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-policy-fine-grained-knowledge-feedback-for","slug":"on-policy-fine-grained-knowledge-feedback-for","title":"On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation","date":"2024-06-18","arxiv_id":"2406.12221","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-policy-fine-grained-knowledge-feedback-for#ran","syntology_url":"https://syntology.ai/paper/2406.12221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12221"}},"official":null}},{"url":"/paper/multimodal-needle-in-a-haystack-benchmarking","slug":"multimodal-needle-in-a-haystack-benchmarking","title":"Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11230","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-needle-in-a-haystack-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.11230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11230"}},"official":{"repos":["wang-ml-lab/multimodal-needle-in-a-haystack"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mdpo-conditional-preference-optimization-for","slug":"mdpo-conditional-preference-optimization-for","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11839","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mdpo-conditional-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.11839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11839"}},"official":{"repos":["luka-group/mDPO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/autohallusion-automatic-generation-of","slug":"autohallusion-automatic-generation-of","title":"AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models","date":"2024-06-16","arxiv_id":"2406.10900","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autohallusion-automatic-generation-of#ran","syntology_url":"https://syntology.ai/paper/2406.10900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10900"}},"official":{"repos":["wuxiyang1996/AutoHallusion"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/understanding-hallucinations-in-diffusion","slug":"understanding-hallucinations-in-diffusion","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","date":"2024-06-13","arxiv_id":"2406.09358","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-hallucinations-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.09358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09358"}},"official":{"repos":["locuslab/diffusion-model-hallucination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-probabilistic-framework-for-llm","slug":"a-probabilistic-framework-for-llm","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","date":"2024-06-11","arxiv_id":"2406.06950","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-probabilistic-framework-for-llm#ran","syntology_url":"https://syntology.ai/paper/2406.06950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06950"}},"official":{"repos":["ucsb-nlp-chang/btprop"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/image-textualization-an-automatic-framework","slug":"image-textualization-an-automatic-framework","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","date":"2024-06-11","arxiv_id":"2406.07502","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/image-textualization-an-automatic-framework#ran","syntology_url":"https://syntology.ai/paper/2406.07502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07502"}},"official":{"repos":["sterzhang/image-textualization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domainrag-a-chinese-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.05654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05654"}},"official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crag-comprehensive-rag-benchmark#ran","syntology_url":"https://syntology.ai/paper/2406.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04744"}},"official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-on-parameter-efficient","slug":"an-empirical-study-on-parameter-efficient","title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","date":"2024-06-07","arxiv_id":"2406.05130","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-empirical-study-on-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.05130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05130"}},"official":{"repos":["alenai97/peft-mllm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-grand-towards-better-grounding-and-less","slug":"3d-grand-towards-better-grounding-and-less","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","date":"2024-06-07","arxiv_id":"2406.05132","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-grand-towards-better-grounding-and-less#ran","syntology_url":"https://syntology.ai/paper/2406.05132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05132"}},"official":{"repos":["sled-group/3D-GRAND"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-noise-robustness-of-retrieval","slug":"enhancing-noise-robustness-of-retrieval","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","date":"2024-05-31","arxiv_id":"2405.20978","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-noise-robustness-of-retrieval#ran","syntology_url":"https://syntology.ai/paper/2405.20978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20978"}},"official":{"repos":["calubkk/raat"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/anah-analytical-annotation-of-hallucinations","slug":"anah-analytical-annotation-of-hallucinations","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","date":"2024-05-30","arxiv_id":"2405.20315","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/anah-analytical-annotation-of-hallucinations#ran","syntology_url":"https://syntology.ai/paper/2405.20315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20315"}},"official":{"repos":["open-compass/anah"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/timechara-evaluating-point-in-time-character","slug":"timechara-evaluating-point-in-time-character","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","date":"2024-05-28","arxiv_id":"2405.18027","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/timechara-evaluating-point-in-time-character#ran","syntology_url":"https://syntology.ai/paper/2405.18027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18027"}},"official":{"repos":["ahnjaewoo/timechara"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-object-hallucination-via-data","slug":"mitigating-object-hallucination-via-data","title":"Data-augmented phrase-level alignment for mitigating object hallucination","date":"2024-05-28","arxiv_id":"2405.18654","repositories_listed":0,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-object-hallucination-via-data#ran","syntology_url":"https://syntology.ai/paper/2405.18654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18654"}},"official":null}},{"url":"/paper/personalized-steering-of-large-language","slug":"personalized-steering-of-large-language","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","date":"2024-05-28","arxiv_id":"2406.00045","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/personalized-steering-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.00045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00045"}},"official":{"repos":["CaoYuanpu/BiPO"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","slug":"rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","arxiv_id":"2405.17220","repositories_listed":5,"syntology":{"n":22,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":17,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rlaif-v-aligning-mllms-through-open-source-ai#ran","syntology_url":"https://syntology.ai/paper/2405.17220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17220"}},"official":{"repos":["openbmb/omnilmm","rlhf-v/rlaif-v"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deem-diffusion-models-serve-as-the-eyes-of","slug":"deem-diffusion-models-serve-as-the-eyes-of","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","date":"2024-05-24","arxiv_id":"2405.15232","repositories_listed":2,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/deem-diffusion-models-serve-as-the-eyes-of#ran","syntology_url":"https://syntology.ai/paper/2405.15232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15232"}},"official":{"repos":["rainbowluocs/deem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/vdgd-mitigating-lvlm-hallucinations-in","slug":"vdgd-mitigating-lvlm-hallucinations-in","title":"Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs","date":"2024-05-24","arxiv_id":"2405.15683","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vdgd-mitigating-lvlm-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2405.15683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15683"}},"official":{"repos":["sreyan88/vdgd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/enhancing-visual-language-modality-alignment","slug":"enhancing-visual-language-modality-alignment","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","date":"2024-05-24","arxiv_id":"2405.15973","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-visual-language-modality-alignment#ran","syntology_url":"https://syntology.ai/paper/2405.15973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15973"}},"official":{"repos":["umd-huang-lab/sima"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/refchecker-reference-based-fine-grained","slug":"refchecker-reference-based-fine-grained","title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14486","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/refchecker-reference-based-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2405.14486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14486"}},"official":{"repos":["amazon-science/refchecker"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/calibrated-self-rewarding-vision-language","slug":"calibrated-self-rewarding-vision-language","title":"Calibrated Self-Rewarding Vision Language Models","date":"2024-05-23","arxiv_id":"2405.14622","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/calibrated-self-rewarding-vision-language#ran","syntology_url":"https://syntology.ai/paper/2405.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14622"}},"official":{"repos":["yiyangzhou/csr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wise-rethinking-the-knowledge-memory-for","slug":"wise-rethinking-the-knowledge-memory-for","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","date":"2024-05-23","arxiv_id":"2405.14768","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/wise-rethinking-the-knowledge-memory-for#ran","syntology_url":"https://syntology.ai/paper/2405.14768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14768"}},"official":{"repos":["zjunlp/easyedit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-multi-level-preference-for-mllms","slug":"automated-multi-level-preference-for-mllms","title":"Automated Multi-level Preference for MLLMs","date":"2024-05-18","arxiv_id":"2405.11165","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automated-multi-level-preference-for-mllms#ran","syntology_url":"https://syntology.ai/paper/2405.11165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11165"}},"official":{"repos":["takomc/amp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rag-and-rau-a-survey-on-retrieval-augmented","slug":"rag-and-rau-a-survey-on-retrieval-augmented","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","date":"2024-04-30","arxiv_id":"2404.19543","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rag-and-rau-a-survey-on-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.19543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19543"}},"official":{"repos":["2471023025/ralm_survey"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/retrieval-head-mechanistically-explains-long","slug":"retrieval-head-mechanistically-explains-long","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","date":"2024-04-24","arxiv_id":"2404.15574","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-head-mechanistically-explains-long#ran","syntology_url":"https://syntology.ai/paper/2404.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15574"}},"official":{"repos":["nightdessert/retrieval_head"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generate-on-graph-treat-llm-as-both-agent-and","slug":"generate-on-graph-treat-llm-as-both-agent-and","title":"Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering","date":"2024-04-23","arxiv_id":"2404.14741","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generate-on-graph-treat-llm-as-both-agent-and#ran","syntology_url":"https://syntology.ai/paper/2404.14741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14741"}},"official":{"repos":["yaooxu/gog"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-and-mitigating-hallucination-in","slug":"detecting-and-mitigating-hallucination-in","title":"Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback","date":"2024-04-22","arxiv_id":"2404.14233","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/detecting-and-mitigating-hallucination-in#ran","syntology_url":"https://syntology.ai/paper/2404.14233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14233"}},"official":{"repos":["Mr-Loevan/HSA-DPO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-large-language-models-as-copilots-for","slug":"towards-large-language-models-as-copilots-for","title":"Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean","date":"2024-04-18","arxiv_id":"2404.12534","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-large-language-models-as-copilots-for#ran","syntology_url":"https://syntology.ai/paper/2404.12534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12534"}},"official":{"repos":["lean-dojo/leancopilot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memllm-finetuning-llms-to-use-an-explicit","slug":"memllm-finetuning-llms-to-use-an-explicit","title":"MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory","date":"2024-04-17","arxiv_id":"2404.11672","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/memllm-finetuning-llms-to-use-an-explicit#ran","syntology_url":"https://syntology.ai/paper/2404.11672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11672"}},"official":{"repos":["amodaresi/memllm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for","slug":"benchmarking-llama2-mistral-gemma-and-gpt-for","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","date":"2024-04-15","arxiv_id":"2404.09785","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-llama2-mistral-gemma-and-gpt-for#ran","syntology_url":"https://syntology.ai/paper/2404.09785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09785"}},"official":{"repos":["innodatalabs/innodata-llm-safety"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/constructing-benchmarks-and-interventions-for","slug":"constructing-benchmarks-and-interventions-for","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","date":"2024-04-15","arxiv_id":"2404.09971","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/constructing-benchmarks-and-interventions-for#ran","syntology_url":"https://syntology.ai/paper/2404.09971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09971"}},"official":{"repos":["technion-cs-nlp/hallucination-mitigation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/view-selection-for-3d-captioning-via","slug":"view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/view-selection-for-3d-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2404.07984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07984"}},"official":null}},{"url":"/paper/tackling-structural-hallucination-in-image","slug":"tackling-structural-hallucination-in-image","title":"Tackling Structural Hallucination in Image Translation with Local Diffusion","date":"2024-04-09","arxiv_id":"2404.05980","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":4,"n_no_contract":5,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 4 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tackling-structural-hallucination-in-image#ran","syntology_url":"https://syntology.ai/paper/2404.05980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05980"}},"official":{"repos":["edshkim98/localdiffusion-hallucination"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pollmgraph-unraveling-hallucinations-in-large","slug":"pollmgraph-unraveling-hallucinations-in-large","title":"PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics","date":"2024-04-06","arxiv_id":"2404.04722","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pollmgraph-unraveling-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2404.04722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04722"}},"official":{"repos":["hitum-dev/pollmgraph"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/knowhalu-hallucination-detection-via-multi","slug":"knowhalu-hallucination-detection-via-multi","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","date":"2024-04-03","arxiv_id":"2404.02935","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knowhalu-hallucination-detection-via-multi#ran","syntology_url":"https://syntology.ai/paper/2404.02935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02935"}},"official":{"repos":["javyduck/knowhalu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-the-general-agent-capabilities-of","slug":"enhancing-the-general-agent-capabilities-of","title":"Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning","date":"2024-03-29","arxiv_id":"2403.19962","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-the-general-agent-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2403.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19962"}},"official":{"repos":["haiv-lab/llm-tmbr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-large-language-models-hallucination-with","slug":"on-large-language-models-hallucination-with","title":"On Large Language Models' Hallucination with Regard to Known Facts","date":"2024-03-29","arxiv_id":"2403.20009","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-large-language-models-hallucination-with#ran","syntology_url":"https://syntology.ai/paper/2403.20009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20009"}},"official":{"repos":["dcdsf321/known_fact_hallucination"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-correctness-without-prompting","slug":"learning-from-correctness-without-prompting","title":"Learning From Correctness Without Prompting Makes LLM Efficient Reasoner","date":"2024-03-28","arxiv_id":"2403.19094","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-from-correctness-without-prompting#ran","syntology_url":"https://syntology.ai/paper/2403.19094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19094"}},"official":{"repos":["starrYYxuan/LeCo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/are-large-language-models-good-at-utility","slug":"are-large-language-models-good-at-utility","title":"Are Large Language Models Good at Utility Judgments?","date":"2024-03-28","arxiv_id":"2403.19216","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/are-large-language-models-good-at-utility#ran","syntology_url":"https://syntology.ai/paper/2403.19216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19216"}},"official":{"repos":["ict-bigdatalab/utility_judgments"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-enhanced-knowledge-editing-for","slug":"retrieval-enhanced-knowledge-editing-for","title":"Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering","date":"2024-03-28","arxiv_id":"2403.19631","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/retrieval-enhanced-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2403.19631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19631"}},"official":{"repos":["sycny/rae"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mechanisms-of-non-factual-hallucinations-in","slug":"mechanisms-of-non-factual-hallucinations-in","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","date":"2024-03-27","arxiv_id":"2403.18167","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mechanisms-of-non-factual-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2403.18167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18167"}},"official":{"repos":["jadeleiyu/lm_hallucination_mechanisms"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-diffusion-based-generative-equalizer-for","slug":"a-diffusion-based-generative-equalizer-for","title":"A Diffusion-Based Generative Equalizer for Music Restoration","date":"2024-03-27","arxiv_id":"2403.18636","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-diffusion-based-generative-equalizer-for#ran","syntology_url":"https://syntology.ai/paper/2403.18636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18636"}},"official":{"repos":["eloimoliner/babe2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-action-faithful-and-multimodal","slug":"chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","arxiv_id":"2403.17359","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-action-faithful-and-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.17359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17359"}},"official":{"repos":["MAGICS-LAB/Chain-of-Actions"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/urbanvlp-a-multi-granularity-vision-language","slug":"urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","arxiv_id":"2403.16831","repositories_listed":2,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":3,"n_no_contract":8,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 3 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/urbanvlp-a-multi-granularity-vision-language#ran","syntology_url":"https://syntology.ai/paper/2403.16831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16831"}},"official":{"repos":["citymind-lab/urbanvlp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/circuit-transformer-end-to-end-circuit-design","slug":"circuit-transformer-end-to-end-circuit-design","title":"Circuit Transformer: A Transformer That Preserves Logical Equivalence","date":"2024-03-14","arxiv_id":"2403.13838","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/circuit-transformer-end-to-end-circuit-design#ran","syntology_url":"https://syntology.ai/paper/2403.13838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13838"}},"official":{"repos":["snowkylin/circuit-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-real-time-hallucination","slug":"unsupervised-real-time-hallucination","title":"Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models","date":"2024-03-11","arxiv_id":"2403.06448","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-real-time-hallucination#ran","syntology_url":"https://syntology.ai/paper/2403.06448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06448"}},"official":{"repos":["oneal2000/mind"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/erbench-an-entity-relationship-based","slug":"erbench-an-entity-relationship-based","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","date":"2024-03-08","arxiv_id":"2403.05266","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/erbench-an-entity-relationship-based#ran","syntology_url":"https://syntology.ai/paper/2403.05266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05266"}},"official":{"repos":["dilab-kaist/erbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowagent-knowledge-augmented-planning-for","slug":"knowagent-knowledge-augmented-planning-for","title":"KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents","date":"2024-03-05","arxiv_id":"2403.03101","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowagent-knowledge-augmented-planning-for#ran","syntology_url":"https://syntology.ai/paper/2403.03101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03101"}},"official":{"repos":["zjunlp/knowagent"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cr-lt-kgqa-a-knowledge-graph-question","slug":"cr-lt-kgqa-a-knowledge-graph-question","title":"CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge","date":"2024-03-03","arxiv_id":"2403.01395","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cr-lt-kgqa-a-knowledge-graph-question#ran","syntology_url":"https://syntology.ai/paper/2403.01395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01395"}},"official":{"repos":["d3mlab/cr-lt-kgqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-sharpness-as-alerts-an-inner","slug":"in-context-sharpness-as-alerts-an-inner","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","date":"2024-03-03","arxiv_id":"2403.01548","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-context-sharpness-as-alerts-an-inner#ran","syntology_url":"https://syntology.ai/paper/2403.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01548"}},"official":{"repos":["hkust-nlp/activation_decoding"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/halc-object-hallucination-reduction-via","slug":"halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","arxiv_id":"2403.00425","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/halc-object-hallucination-reduction-via#ran","syntology_url":"https://syntology.ai/paper/2403.00425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00425"}},"official":{"repos":["billchan226/halc","bradyfu/awesome-multimodal-large-language-models"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/self-consistent-decoding-for-more-factual","slug":"self-consistent-decoding-for-more-factual","title":"Self-Consistent Decoding for More Factual Open Responses","date":"2024-03-01","arxiv_id":"2403.00696","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-consistent-decoding-for-more-factual#ran","syntology_url":"https://syntology.ai/paper/2403.00696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00696"}},"official":{"repos":["cdmalon/selfconsistent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-all-seeing-project-v2-towards-general","slug":"the-all-seeing-project-v2-towards-general","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","date":"2024-02-29","arxiv_id":"2402.19474","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-all-seeing-project-v2-towards-general#ran","syntology_url":"https://syntology.ai/paper/2402.19474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19474"}},"official":{"repos":["opengvlab/all-seeing"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-machine-generated-texts-by-multi","slug":"detecting-machine-generated-texts-by-multi","title":"Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy","date":"2024-02-25","arxiv_id":"2402.16041","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/detecting-machine-generated-texts-by-multi#ran","syntology_url":"https://syntology.ai/paper/2402.16041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16041"}},"official":{"repos":["zshsh98/mmd-mp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/seeing-is-believing-mitigating-hallucination#ran","syntology_url":"https://syntology.ai/paper/2402.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15300"}},"official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/a-data-centric-approach-to-generate-faithful","slug":"a-data-centric-approach-to-generate-faithful","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","date":"2024-02-23","arxiv_id":"2402.15422","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-data-centric-approach-to-generate-faithful#ran","syntology_url":"https://syntology.ai/paper/2402.15422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15422"}},"official":{"repos":["stefanhgm/patient_summaries_with_llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/less-is-more-mitigating-multimodal","slug":"less-is-more-mitigating-multimodal","title":"Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective","date":"2024-02-22","arxiv_id":"2402.14545","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/less-is-more-mitigating-multimodal#ran","syntology_url":"https://syntology.ai/paper/2402.14545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14545"}},"official":{"repos":["yuezih/less-is-more"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-hallucinations-of-multi-modal-large","slug":"visual-hallucinations-of-multi-modal-large","title":"Visual Hallucinations of Multi-modal Large Language Models","date":"2024-02-22","arxiv_id":"2402.14683","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-hallucinations-of-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2402.14683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14683"}},"official":{"repos":["wenhuang2000/vhtest"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dualfocus-integrating-macro-and-micro","slug":"dualfocus-integrating-macro-and-micro","title":"DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models","date":"2024-02-22","arxiv_id":"2402.14767","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dualfocus-integrating-macro-and-micro#ran","syntology_url":"https://syntology.ai/paper/2402.14767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14767"}},"official":{"repos":["InternLM/InternLM-XComposer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reformatted-alignment","slug":"reformatted-alignment","title":"Reformatted Alignment","date":"2024-02-19","arxiv_id":"2402.12219","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reformatted-alignment#ran","syntology_url":"https://syntology.ai/paper/2402.12219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12219"}},"official":{"repos":["gair-nlp/realign"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-modalities-in-vision-large-language","slug":"aligning-modalities-in-vision-large-language","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","date":"2024-02-18","arxiv_id":"2402.11411","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-modalities-in-vision-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.11411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11411"}},"official":{"repos":["yiyangzhou/povid"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efuf-efficient-fine-grained-unlearning","slug":"efuf-efficient-fine-grained-unlearning","title":"EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models","date":"2024-02-15","arxiv_id":"2402.09801","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efuf-efficient-fine-grained-unlearning#ran","syntology_url":"https://syntology.ai/paper/2402.09801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09801"}},"official":{"repos":["starreeze/efuf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-decomposition-and-quantification","slug":"uncertainty-decomposition-and-quantification","title":"Uncertainty Quantification for In-Context Learning of Large Language Models","date":"2024-02-15","arxiv_id":"2402.10189","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncertainty-decomposition-and-quantification#ran","syntology_url":"https://syntology.ai/paper/2402.10189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10189"}},"official":{"repos":["lingchen0331/uq_icl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/g-retriever-retrieval-augmented-generation","slug":"g-retriever-retrieval-augmented-generation","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","date":"2024-02-12","arxiv_id":"2402.07630","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/g-retriever-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2402.07630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07630"}},"official":{"repos":["xiaoxinhe/g-retriever"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prismatic-vlms-investigating-the-design-space","slug":"prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","arxiv_id":"2402.07865","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prismatic-vlms-investigating-the-design-space#ran","syntology_url":"https://syntology.ai/paper/2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"official":{"repos":["tri-ml/prismatic-vlms","tri-ml/vlm-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/poisonedrag-knowledge-poisoning-attacks-to","slug":"poisonedrag-knowledge-poisoning-attacks-to","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-02-12","arxiv_id":"2402.07867","repositories_listed":2,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/poisonedrag-knowledge-poisoning-attacks-to#ran","syntology_url":"https://syntology.ai/paper/2402.07867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07867"}},"official":{"repos":["sleeepeer/poisonedrag"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/resumeflow-an-llm-facilitated-pipeline-for","slug":"resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","arxiv_id":"2402.06221","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/resumeflow-an-llm-facilitated-pipeline-for#ran","syntology_url":"https://syntology.ai/paper/2402.06221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06221"}},"official":{"repos":["Ztrimus/job-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/introspective-planning-guiding-language","slug":"introspective-planning-guiding-language","title":"Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity","date":"2024-02-09","arxiv_id":"2402.06529","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/introspective-planning-guiding-language#ran","syntology_url":"https://syntology.ai/paper/2402.06529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06529"}},"official":{"repos":["kevinliang888/IntroPlan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-instinctive-bias-spurious-images-lead-to","slug":"the-instinctive-bias-spurious-images-lead-to","title":"The Instinctive Bias: Spurious Images lead to Illusion in MLLMs","date":"2024-02-06","arxiv_id":"2402.03757","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-instinctive-bias-spurious-images-lead-to#ran","syntology_url":"https://syntology.ai/paper/2402.03757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03757"}},"official":{"repos":["masaiahhan/correlationqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/training-language-models-to-generate-text","slug":"training-language-models-to-generate-text","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","date":"2024-02-06","arxiv_id":"2402.04315","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/training-language-models-to-generate-text#ran","syntology_url":"https://syntology.ai/paper/2402.04315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04315"}},"official":{"repos":["hcy123902/atg-w-fg-rw"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unified-hallucination-detection-for","slug":"unified-hallucination-detection-for","title":"Unified Hallucination Detection for Multimodal Large Language Models","date":"2024-02-05","arxiv_id":"2402.03190","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unified-hallucination-detection-for#ran","syntology_url":"https://syntology.ai/paper/2402.03190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03190"}},"official":{"repos":["openkg-org/easydetect","zjunlp/easydetect"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llamp-large-language-model-made-powerful-for","slug":"llamp-large-language-model-made-powerful-for","title":"LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation","date":"2024-01-30","arxiv_id":"2401.17244","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llamp-large-language-model-made-powerful-for#ran","syntology_url":"https://syntology.ai/paper/2401.17244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17244"}},"official":{"repos":["chiang-yuan/llamp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/k-qa-a-real-world-medical-q-a-benchmark","slug":"k-qa-a-real-world-medical-q-a-benchmark","title":"K-QA: A Real-World Medical Q&A Benchmark","date":"2024-01-25","arxiv_id":"2401.14493","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/k-qa-a-real-world-medical-q-a-benchmark#ran","syntology_url":"https://syntology.ai/paper/2401.14493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14493"}},"official":{"repos":["itaymanes/k-qa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-hallucinations-of-large-language","slug":"mitigating-hallucinations-of-large-language","title":"Knowledge Verification to Nip Hallucination in the Bud","date":"2024-01-19","arxiv_id":"2401.10768","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":5,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mitigating-hallucinations-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2401.10768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10768"}},"official":{"repos":["fanqiwan/kca"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/hallucination-benchmark-in-medical-visual","slug":"hallucination-benchmark-in-medical-visual","title":"Hallucination Benchmark in Medical Visual Question Answering","date":"2024-01-11","arxiv_id":"2401.05827","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hallucination-benchmark-in-medical-visual#ran","syntology_url":"https://syntology.ai/paper/2401.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05827"}},"official":{"repos":["knowlab/halt-medvqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sh2-self-highlighted-hesitation-helps-you","slug":"sh2-self-highlighted-hesitation-helps-you","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","date":"2024-01-11","arxiv_id":"2401.05930","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/sh2-self-highlighted-hesitation-helps-you#ran","syntology_url":"https://syntology.ai/paper/2401.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05930"}},"official":{"repos":["0-kaikai-0/sh2","LUMIA-Group/SH2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/the-dawn-after-the-dark-an-empirical-study-on","slug":"the-dawn-after-the-dark-an-empirical-study-on","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","date":"2024-01-06","arxiv_id":"2401.03205","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-dawn-after-the-dark-an-empirical-study-on#ran","syntology_url":"https://syntology.ai/paper/2401.03205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03205"}},"official":{"repos":["rucaibox/halueval-2.0"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ragtruth-a-hallucination-corpus-for","slug":"ragtruth-a-hallucination-corpus-for","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","date":"2023-12-31","arxiv_id":"2401.00396","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ragtruth-a-hallucination-corpus-for#ran","syntology_url":"https://syntology.ai/paper/2401.00396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00396"}},"official":{"repos":["particlemedia/ragtruth"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/alleviating-hallucinations-of-large-language","slug":"alleviating-hallucinations-of-large-language","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","date":"2023-12-25","arxiv_id":"2312.15710","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/alleviating-hallucinations-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.15710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15710"}},"official":{"repos":["hiyouga/llama-factory","hillzhang1999/icd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/melo-enhancing-model-editing-with-neuron","slug":"melo-enhancing-model-editing-with-neuron","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","date":"2023-12-19","arxiv_id":"2312.11795","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/melo-enhancing-model-editing-with-neuron#ran","syntology_url":"https://syntology.ai/paper/2312.11795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11795"}},"official":{"repos":["bruthyu/melo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-early-detection-of-hallucinations-in","slug":"on-early-detection-of-hallucinations-in","title":"On Early Detection of Hallucinations in Factual Question Answering","date":"2023-12-19","arxiv_id":"2312.14183","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-early-detection-of-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2312.14183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14183"}},"official":{"repos":["amazon-science/llm-hallucinations-factual-qa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/nomiracl-knowing-when-you-don-t-know-for","slug":"nomiracl-knowing-when-you-don-t-know-for","title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","date":"2023-12-18","arxiv_id":"2312.11361","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/nomiracl-knowing-when-you-don-t-know-for#ran","syntology_url":"https://syntology.ai/paper/2312.11361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11361"}},"official":{"repos":["project-miracl/nomiracl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hallucination-augmented-contrastive-learning","slug":"hallucination-augmented-contrastive-learning","title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model","date":"2023-12-12","arxiv_id":"2312.06968","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hallucination-augmented-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2312.06968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06968"}},"official":{"repos":["x-plug/mplug-halowl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/towards-stable-and-faithful-inpainting","slug":"towards-stable-and-faithful-inpainting","title":"Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency","date":"2023-12-08","arxiv_id":"2312.04831","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-stable-and-faithful-inpainting#ran","syntology_url":"https://syntology.ai/paper/2312.04831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04831"}},"official":{"repos":["yikai-wang/asuka-misato"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mocha-multi-objective-reinforcement","slug":"mocha-multi-objective-reinforcement","title":"Mitigating Open-Vocabulary Caption Hallucinations","date":"2023-12-06","arxiv_id":"2312.03631","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mocha-multi-objective-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.03631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03631"}},"official":{"repos":["assafbk/mocha_code"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/weakly-supervised-detection-of-hallucinations","slug":"weakly-supervised-detection-of-hallucinations","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","date":"2023-12-05","arxiv_id":"2312.02798","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/weakly-supervised-detection-of-hallucinations#ran","syntology_url":"https://syntology.ai/paper/2312.02798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02798"}},"official":{"repos":["Trusted-AI/adversarial-robustness-toolbox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/behind-the-magic-merlim-multi-modal","slug":"behind-the-magic-merlim-multi-modal","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models","date":"2023-12-03","arxiv_id":"2312.02219","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/behind-the-magic-merlim-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2312.02219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02219"}},"official":{"repos":["ojedaf/merlim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/opera-alleviating-hallucination-in-multi","slug":"opera-alleviating-hallucination-in-multi","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","date":"2023-11-29","arxiv_id":"2311.17911","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/opera-alleviating-hallucination-in-multi#ran","syntology_url":"https://syntology.ai/paper/2311.17911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17911"}},"official":{"repos":["shikiw/opera"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/beyond-hallucinations-enhancing-lvlms-through","slug":"beyond-hallucinations-enhancing-lvlms-through","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","date":"2023-11-28","arxiv_id":"2311.16839","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-hallucinations-enhancing-lvlms-through#ran","syntology_url":"https://syntology.ai/paper/2311.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16839"}},"official":{"repos":["opendatalab/ha-dpo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-object-hallucinations-in-large","slug":"mitigating-object-hallucinations-in-large","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","date":"2023-11-28","arxiv_id":"2311.16922","repositories_listed":7,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-object-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2311.16922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16922"}},"official":{"repos":["bradyfu/awesome-multimodal-large-language-models","damo-nlp-sg/vcd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uhgeval-benchmarking-the-hallucination-of","slug":"uhgeval-benchmarking-the-hallucination-of","title":"UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation","date":"2023-11-26","arxiv_id":"2311.15296","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uhgeval-benchmarking-the-hallucination-of#ran","syntology_url":"https://syntology.ai/paper/2311.15296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15296"}},"official":{"repos":["IAAR-Shanghai/UHGEval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-uncertainty-based-hallucination","slug":"enhancing-uncertainty-based-hallucination","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","date":"2023-11-22","arxiv_id":"2311.13230","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-uncertainty-based-hallucination#ran","syntology_url":"https://syntology.ai/paper/2311.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13230"}},"official":{"repos":["zthang/focus"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hallucidoctor-mitigating-hallucinatory","slug":"hallucidoctor-mitigating-hallucinatory","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","date":"2023-11-22","arxiv_id":"2311.13614","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/hallucidoctor-mitigating-hallucinatory#ran","syntology_url":"https://syntology.ai/paper/2311.13614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13614"}},"official":{"repos":["yuqifan1117/hallucidoctor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/r-tuning-teaching-large-language-models-to","slug":"r-tuning-teaching-large-language-models-to","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","date":"2023-11-16","arxiv_id":"2311.09677","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":16,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/r-tuning-teaching-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2311.09677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09677"}},"official":{"repos":["shizhediao/r-tuning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/volcano-mitigating-multimodal-hallucination","slug":"volcano-mitigating-multimodal-hallucination","title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","date":"2023-11-13","arxiv_id":"2311.07362","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/volcano-mitigating-multimodal-hallucination#ran","syntology_url":"https://syntology.ai/paper/2311.07362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07362"}},"official":{"repos":["kaistai/volcano"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"0a54a3cd42eb1d278ecd48ec01ebaa100d7174d23f7cabea2594b04539a93280","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}