{"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/6","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":6,"pages_in_order":19,"rows_per_page":100,"rows":[501,600],"of":1816,"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","prev":"/task/hallucination/papers/5","next":"/task/hallucination/papers/7","papers":[{"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/science-checker-reloaded-a-bidirectional","slug":"science-checker-reloaded-a-bidirectional","title":"Science Checker Reloaded: A Bidirectional Paradigm for Transparency and Logical Reasoning","date":"2024-02-21","arxiv_id":"2402.13897","repositories_listed":1,"syntology":null},{"url":"/paper/owsm-ctc-an-open-encoder-only-speech","slug":"owsm-ctc-an-open-encoder-only-speech","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","date":"2024-02-20","arxiv_id":"2402.12654","repositories_listed":1,"syntology":null},{"url":"/paper/tofueval-evaluating-hallucinations-of-llms-on","slug":"tofueval-evaluating-hallucinations-of-llms-on","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","date":"2024-02-20","arxiv_id":"2402.13249","repositories_listed":1,"syntology":null},{"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/eventrl-enhancing-event-extraction-with","slug":"eventrl-enhancing-event-extraction-with","title":"EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models","date":"2024-02-18","arxiv_id":"2402.11430","repositories_listed":1,"syntology":null},{"url":"/paper/logical-closed-loop-uncovering-object","slug":"logical-closed-loop-uncovering-object","title":"Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models","date":"2024-02-18","arxiv_id":"2402.11622","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/logical-closed-loop-uncovering-object#ran","syntology_url":"https://syntology.ai/paper/2402.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11622"}},"official":{"repos":["hyperwjf/logiccheckgpt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/when-dataflow-analysis-meets-large-language","slug":"when-dataflow-analysis-meets-large-language","title":"LLMDFA: Analyzing Dataflow in Code with Large Language Models","date":"2024-02-16","arxiv_id":"2402.10754","repositories_listed":1,"syntology":null},{"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/visually-dehallucinative-instruction-1","slug":"visually-dehallucinative-instruction-1","title":"Visually Dehallucinative Instruction Generation: Know What You Don't Know","date":"2024-02-15","arxiv_id":"2402.09717","repositories_listed":1,"syntology":null},{"url":"/paper/into-the-unknown-self-learning-large-language","slug":"into-the-unknown-self-learning-large-language","title":"Into the Unknown: Self-Learning Large Language Models","date":"2024-02-14","arxiv_id":"2402.09147","repositories_listed":1,"syntology":null},{"url":"/paper/instructgraph-boosting-large-language-models","slug":"instructgraph-boosting-large-language-models","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","date":"2024-02-13","arxiv_id":"2402.08785","repositories_listed":1,"syntology":null},{"url":"/paper/visually-dehallucinative-instruction","slug":"visually-dehallucinative-instruction","title":"Visually Dehallucinative Instruction Generation","date":"2024-02-13","arxiv_id":"2402.08348","repositories_listed":1,"syntology":null},{"url":"/paper/careless-whisper-speech-to-text-hallucination","slug":"careless-whisper-speech-to-text-hallucination","title":"Careless Whisper: Speech-to-Text Hallucination Harms","date":"2024-02-12","arxiv_id":"2402.08021","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-goes-to-med-school-exploring-the","slug":"gemini-goes-to-med-school-exploring-the","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","date":"2024-02-10","arxiv_id":"2402.07023","repositories_listed":1,"syntology":null},{"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/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/vigor-improving-visual-grounding-of-large","slug":"vigor-improving-visual-grounding-of-large","title":"ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling","date":"2024-02-09","arxiv_id":"2402.06118","repositories_listed":1,"syntology":null},{"url":"/paper/inside-llms-internal-states-retain-the-power","slug":"inside-llms-internal-states-retain-the-power","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","date":"2024-02-06","arxiv_id":"2402.03744","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/inside-llms-internal-states-retain-the-power#ran","syntology_url":"https://syntology.ai/paper/2402.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03744"}},"official":{"repos":["alibaba/eigenscore"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"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/llm-enhanced-data-management","slug":"llm-enhanced-data-management","title":"LLM-Enhanced Data Management","date":"2024-02-04","arxiv_id":"2402.02643","repositories_listed":1,"syntology":null},{"url":"/paper/pokellmon-a-human-parity-agent-for-pokemon","slug":"pokellmon-a-human-parity-agent-for-pokemon","title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01118","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-hallucination-in-large-vision","slug":"a-survey-on-hallucination-in-large-vision","title":"A Survey on Hallucination in Large Vision-Language Models","date":"2024-02-01","arxiv_id":"2402.00253","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-makes-a-difference","slug":"instruction-makes-a-difference","title":"Instruction Makes a Difference","date":"2024-02-01","arxiv_id":"2402.00453","repositories_listed":1,"syntology":null},{"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/medtss-transforming-abstractive-summarization","slug":"medtss-transforming-abstractive-summarization","title":"MedTSS: transforming abstractive summarization of scientific articles with linguistic analysis and concept reinforcement","date":"2024-01-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/when-large-language-models-meet-vector","slug":"when-large-language-models-meet-vector","title":"When Large Language Models Meet Vector Databases: A Survey","date":"2024-01-30","arxiv_id":"2402.01763","repositories_listed":1,"syntology":null},{"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/fine-grained-contract-ner-using-instruction","slug":"fine-grained-contract-ner-using-instruction","title":"Fine-grained Contract NER using instruction based model","date":"2024-01-24","arxiv_id":"2401.13545","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-can-large-language-models-explain","slug":"how-well-can-large-language-models-explain","title":"How well can a large language model explain business processes as perceived by users?","date":"2024-01-23","arxiv_id":"2401.12846","repositories_listed":1,"syntology":null},{"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/lighthouse-a-survey-of-agi-hallucination","slug":"lighthouse-a-survey-of-agi-hallucination","title":"LightHouse: A Survey of AGI Hallucination","date":"2024-01-08","arxiv_id":"2401.06792","repositories_listed":1,"syntology":null},{"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/dcr-consistency-divide-conquer-reasoning-for","slug":"dcr-consistency-divide-conquer-reasoning-for","title":"DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models","date":"2024-01-04","arxiv_id":"2401.02132","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-survey-of-hallucination","slug":"a-comprehensive-survey-of-hallucination","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","date":"2024-01-02","arxiv_id":"2401.01313","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-comprehensive-survey-of-hallucination#ran","syntology_url":"https://syntology.ai/paper/2401.01313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01313"}},"official":null}},{"url":"/paper/advancing-ttp-analysis-harnessing-the-power","slug":"advancing-ttp-analysis-harnessing-the-power","title":"Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation","date":"2023-12-30","arxiv_id":"2401.00280","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-decoding-reduces-hallucination","slug":"context-aware-decoding-reduces-hallucination","title":"Context-aware Decoding Reduces Hallucination in Query-focused Summarization","date":"2023-12-21","arxiv_id":"2312.14335","repositories_listed":1,"syntology":null},{"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/improving-factual-error-correction-by","slug":"improving-factual-error-correction-by","title":"Improving Factual Error Correction by Learning to Inject Factual Errors","date":"2023-12-12","arxiv_id":"2312.07049","repositories_listed":1,"syntology":null},{"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/mitigating-fine-grained-hallucination-by-fine","slug":"mitigating-fine-grained-hallucination-by-fine","title":"Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites","date":"2023-12-04","arxiv_id":"2312.01701","repositories_listed":1,"syntology":null},{"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/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/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/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/generalization-and-hallucination-of-large","slug":"generalization-and-hallucination-of-large","title":"Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection","date":"2023-11-19","arxiv_id":"2311.11273","repositories_listed":1,"syntology":null},{"url":"/paper/crafting-in-context-examples-according-to-lms","slug":"crafting-in-context-examples-according-to-lms","title":"Crafting In-context Examples according to LMs' Parametric Knowledge","date":"2023-11-16","arxiv_id":"2311.09579","repositories_listed":1,"syntology":null},{"url":"/paper/deceiving-semantic-shortcuts-on-reasoning","slug":"deceiving-semantic-shortcuts-on-reasoning","title":"Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?","date":"2023-11-16","arxiv_id":"2311.09702","repositories_listed":1,"syntology":null},{"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/ever-mitigating-hallucination-in-large","slug":"ever-mitigating-hallucination-in-large","title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","date":"2023-11-15","arxiv_id":"2311.09114","repositories_listed":1,"syntology":null},{"url":"/paper/how-trustworthy-are-open-source-llms-an","slug":"how-trustworthy-are-open-source-llms-an","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","date":"2023-11-15","arxiv_id":"2311.09447","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/how-trustworthy-are-open-source-llms-an#ran","syntology_url":"https://syntology.ai/paper/2311.09447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09447"}},"official":{"repos":["osu-nlp-group/eval-llm-trust"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/lighter-yet-more-faithful-investigating","slug":"lighter-yet-more-faithful-investigating","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","date":"2023-11-15","arxiv_id":"2311.09335","repositories_listed":1,"syntology":null},{"url":"/paper/an-llm-free-multi-dimensional-benchmark-for","slug":"an-llm-free-multi-dimensional-benchmark-for","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","date":"2023-11-13","arxiv_id":"2311.07397","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/an-llm-free-multi-dimensional-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2311.07397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07397"}},"official":{"repos":["junyangwang0410/amber"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/finding-and-editing-multi-modal-neurons-in","slug":"finding-and-editing-multi-modal-neurons-in","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","date":"2023-11-13","arxiv_id":"2311.07470","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/finding-and-editing-multi-modal-neurons-in#ran","syntology_url":"https://syntology.ai/paper/2311.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07470"}},"official":{"repos":["opanhw/MM_Neurons"],"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/gpt-4v-ision-as-a-social-media-analysis","slug":"gpt-4v-ision-as-a-social-media-analysis","title":"GPT-4V(ision) as A Social Media Analysis Engine","date":"2023-11-13","arxiv_id":"2311.07547","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-multi-pivot-ensembling-with","slug":"investigating-multi-pivot-ensembling-with","title":"Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models","date":"2023-11-13","arxiv_id":"2311.07439","repositories_listed":1,"syntology":null},{"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"]}}},{"url":"/paper/a-survey-on-hallucination-in-large-language","slug":"a-survey-on-hallucination-in-large-language","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","date":"2023-11-09","arxiv_id":"2311.05232","repositories_listed":1,"syntology":null},{"url":"/paper/holistic-analysis-of-hallucination-in-gpt-4v","slug":"holistic-analysis-of-hallucination-in-gpt-4v","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","date":"2023-11-06","arxiv_id":"2311.03287","repositories_listed":1,"syntology":null},{"url":"/paper/chef-a-comprehensive-evaluation-framework-for","slug":"chef-a-comprehensive-evaluation-framework-for","title":"ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models","date":"2023-11-05","arxiv_id":"2311.02692","repositories_listed":1,"syntology":null},{"url":"/paper/sac-3-reliable-hallucination-detection-in","slug":"sac-3-reliable-hallucination-detection-in","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","date":"2023-11-03","arxiv_id":"2311.01740","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/sac-3-reliable-hallucination-detection-in#ran","syntology_url":"https://syntology.ai/paper/2311.01740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01740"}},"official":{"repos":["intuit/sac3"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/collaborative-large-language-model-for","slug":"collaborative-large-language-model-for","title":"Collaborative Large Language Model for Recommender Systems","date":"2023-11-02","arxiv_id":"2311.01343","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/collaborative-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2311.01343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01343"}},"official":{"repos":["yaochenzhu/llm4rec"],"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/crush4sql-collective-retrieval-using-schema","slug":"crush4sql-collective-retrieval-using-schema","title":"CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQL","date":"2023-11-02","arxiv_id":"2311.01173","repositories_listed":1,"syntology":null},{"url":"/paper/brain-like-flexible-visual-inference-by","slug":"brain-like-flexible-visual-inference-by","title":"Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment","date":"2023-10-31","arxiv_id":"2310.20599","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-imitation-edit-feedback-for-factual","slug":"synthetic-imitation-edit-feedback-for-factual","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","date":"2023-10-30","arxiv_id":"2310.20033","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":3,"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 3 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/synthetic-imitation-edit-feedback-for-factual#ran","syntology_url":"https://syntology.ai/paper/2310.20033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20033"}},"official":{"repos":["seasonyao/learnfromhumanedit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lightlm-a-lightweight-deep-and-narrow","slug":"lightlm-a-lightweight-deep-and-narrow","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","date":"2023-10-26","arxiv_id":"2310.17488","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lightlm-a-lightweight-deep-and-narrow#ran","syntology_url":"https://syntology.ai/paper/2310.17488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17488"}},"official":{"repos":["dongyuanjushi/lightlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/critic-driven-decoding-for-mitigating","slug":"critic-driven-decoding-for-mitigating","title":"Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation","date":"2023-10-25","arxiv_id":"2310.16964","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/critic-driven-decoding-for-mitigating#ran","syntology_url":"https://syntology.ai/paper/2310.16964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16964"}},"official":{"repos":["langus0/critic-aware-decoding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/correction-with-backtracking-reduces","slug":"correction-with-backtracking-reduces","title":"Correction with Backtracking Reduces Hallucination in Summarization","date":"2023-10-24","arxiv_id":"2310.16176","repositories_listed":1,"syntology":null},{"url":"/paper/woodpecker-hallucination-correction-for","slug":"woodpecker-hallucination-correction-for","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","date":"2023-10-24","arxiv_id":"2310.16045","repositories_listed":1,"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":13,"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/woodpecker-hallucination-correction-for#ran","syntology_url":"https://syntology.ai/paper/2310.16045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16045"}},"official":{"repos":["bradyfu/woodpecker"],"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/fidelity-enriched-contrastive-search","slug":"fidelity-enriched-contrastive-search","title":"Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation","date":"2023-10-23","arxiv_id":"2310.14981","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-hallucinate-but-may-excel-at","slug":"language-models-hallucinate-but-may-excel-at","title":"Language Models Hallucinate, but May Excel at Fact Verification","date":"2023-10-23","arxiv_id":"2310.14564","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/language-models-hallucinate-but-may-excel-at#ran","syntology_url":"https://syntology.ai/paper/2310.14564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14564"}},"official":{"repos":["jianguanthu/llmforfv"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/chainpoll-a-high-efficacy-method-for-llm","slug":"chainpoll-a-high-efficacy-method-for-llm","title":"Chainpoll: A high efficacy method for LLM hallucination detection","date":"2023-10-22","arxiv_id":"2310.18344","repositories_listed":1,"syntology":null},{"url":"/paper/maf-multi-aspect-feedback-for-improving","slug":"maf-multi-aspect-feedback-for-improving","title":"MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models","date":"2023-10-19","arxiv_id":"2310.12426","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/maf-multi-aspect-feedback-for-improving#ran","syntology_url":"https://syntology.ai/paper/2310.12426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12426"}},"official":{"repos":["deepakn97/maf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reliable-academic-conference-question","slug":"reliable-academic-conference-question","title":"Reliable Academic Conference Question Answering: A Study Based on Large Language Model","date":"2023-10-19","arxiv_id":"2310.13028","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-siren-s-song-towards-reliable","slug":"unveiling-the-siren-s-song-towards-reliable","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","date":"2023-10-18","arxiv_id":"2310.12086","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/unveiling-the-siren-s-song-towards-reliable#ran","syntology_url":"https://syntology.ai/paper/2310.12086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12086"}},"official":{"repos":["zjunlp/factchd"],"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/lidar-based-4d-occupancy-completion-and","slug":"lidar-based-4d-occupancy-completion-and","title":"LiDAR-based 4D Occupancy Completion and Forecasting","date":"2023-10-17","arxiv_id":"2310.11239","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lidar-based-4d-occupancy-completion-and#ran","syntology_url":"https://syntology.ai/paper/2310.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11239"}},"official":{"repos":["ai4ce/occ4cast"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/factored-verification-detecting-and-reducing","slug":"factored-verification-detecting-and-reducing","title":"Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers","date":"2023-10-16","arxiv_id":"2310.10627","repositories_listed":1,"syntology":null},{"url":"/paper/regavae-a-retrieval-augmented-gaussian","slug":"regavae-a-retrieval-augmented-gaussian","title":"RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling","date":"2023-10-16","arxiv_id":"2310.10567","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/regavae-a-retrieval-augmented-gaussian#ran","syntology_url":"https://syntology.ai/paper/2310.10567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10567"}},"official":{"repos":["trustedllm/regavae"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/theory-of-mind-for-multi-agent-collaboration","slug":"theory-of-mind-for-multi-agent-collaboration","title":"Theory of Mind for Multi-Agent Collaboration via Large Language Models","date":"2023-10-16","arxiv_id":"2310.10701","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-the-reliability-of-large-language","slug":"assessing-the-reliability-of-large-language","title":"Assessing the Reliability of Large Language Model Knowledge","date":"2023-10-15","arxiv_id":"2310.09820","repositories_listed":1,"syntology":null},{"url":"/paper/from-clip-to-dino-visual-encoders-shout-in","slug":"from-clip-to-dino-visual-encoders-shout-in","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","date":"2023-10-13","arxiv_id":"2310.08825","repositories_listed":1,"syntology":null},{"url":"/paper/kcts-knowledge-constrained-tree-search","slug":"kcts-knowledge-constrained-tree-search","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","date":"2023-10-13","arxiv_id":"2310.09044","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/kcts-knowledge-constrained-tree-search#ran","syntology_url":"https://syntology.ai/paper/2310.09044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09044"}},"official":{"repos":["hkust-knowcomp/knowledge-constrained-decoding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/kelly-is-a-warm-person-joseph-is-a-role-model","slug":"kelly-is-a-warm-person-joseph-is-a-role-model","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","date":"2023-10-13","arxiv_id":"2310.09219","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/kelly-is-a-warm-person-joseph-is-a-role-model#ran","syntology_url":"https://syntology.ai/paper/2310.09219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09219"}},"official":{"repos":["uclanlp/biases-llm-reference-letters"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-teach-large-language-models","slug":"learning-to-teach-large-language-models","title":"Improving Large Language Models in Event Relation Logical Prediction","date":"2023-10-13","arxiv_id":"2310.09158","repositories_listed":1,"syntology":null},{"url":"/paper/cp-kgc-constrained-prompt-knowledge-graph","slug":"cp-kgc-constrained-prompt-knowledge-graph","title":"Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement","date":"2023-10-12","arxiv_id":"2310.08279","repositories_listed":1,"syntology":null},{"url":"/paper/gamegpt-multi-agent-collaborative-framework","slug":"gamegpt-multi-agent-collaborative-framework","title":"GameGPT: Multi-agent Collaborative Framework for Game Development","date":"2023-10-12","arxiv_id":"2310.08067","repositories_listed":1,"syntology":null},{"url":"/paper/graphextqa-a-benchmark-for-evaluating-graph","slug":"graphextqa-a-benchmark-for-evaluating-graph","title":"GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models","date":"2023-10-12","arxiv_id":"2310.08487","repositories_listed":1,"syntology":null},{"url":"/paper/opseval-a-comprehensive-task-oriented-aiops","slug":"opseval-a-comprehensive-task-oriented-aiops","title":"OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models","date":"2023-10-11","arxiv_id":"2310.07637","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-benchmark-and-reverse-validation-method","slug":"a-new-benchmark-and-reverse-validation-method","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","date":"2023-10-10","arxiv_id":"2310.06498","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"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) · 3 unverified","sample_list":"/paper/a-new-benchmark-and-reverse-validation-method#ran","syntology_url":"https://syntology.ai/paper/2310.06498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06498"}},"official":{"repos":["maybenotime/phd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-natural-language-inference-for","slug":"chain-of-natural-language-inference-for","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","date":"2023-10-06","arxiv_id":"2310.03951","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/chain-of-natural-language-inference-for#ran","syntology_url":"https://syntology.ai/paper/2310.03951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03951"}},"official":{"repos":["microsoft/conli_hallucination"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agir-automating-cyber-threat-intelligence","slug":"agir-automating-cyber-threat-intelligence","title":"AGIR: Automating Cyber Threat Intelligence Reporting with Natural Language Generation","date":"2023-10-04","arxiv_id":"2310.02655","repositories_listed":1,"syntology":null}],"record_sha256":"8d60151d4299c2077d7d277130ee3d45bc749f6cf3351a35556944e519566d29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}