{"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/large-language-model/papers/15","list_of":"/task/large-language-model","task":"Large Language Model","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":15,"pages_in_order":61,"rows_per_page":100,"rows":[1401,1500],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model","prev":"/task/large-language-model/papers/14","next":"/task/large-language-model/papers/16","papers":[{"url":"/paper/pleak-prompt-leaking-attacks-against-large","slug":"pleak-prompt-leaking-attacks-against-large","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","date":"2024-05-10","arxiv_id":"2405.06823","repositories_listed":1,"syntology":null},{"url":"/paper/saudibert-a-large-language-model-pretrained","slug":"saudibert-a-large-language-model-pretrained","title":"SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora","date":"2024-05-10","arxiv_id":"2405.06239","repositories_listed":1,"syntology":null},{"url":"/paper/llm-qbench-a-benchmark-towards-the-best","slug":"llm-qbench-a-benchmark-towards-the-best","title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","date":"2024-05-09","arxiv_id":"2405.06001","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/llm-qbench-a-benchmark-towards-the-best#ran","syntology_url":"https://syntology.ai/paper/2405.06001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06001"}},"official":{"repos":["modeltc/llmc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/towards-a-path-dependent-account-of-category","slug":"towards-a-path-dependent-account-of-category","title":"Towards a Path Dependent Account of Category Fluency","date":"2024-05-09","arxiv_id":"2405.06714","repositories_listed":1,"syntology":null},{"url":"/paper/fishing-for-magikarp-automatically-detecting","slug":"fishing-for-magikarp-automatically-detecting","title":"Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models","date":"2024-05-08","arxiv_id":"2405.05417","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/fishing-for-magikarp-automatically-detecting#ran","syntology_url":"https://syntology.ai/paper/2405.05417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05417"}},"official":{"repos":["cohere-ai/magikarp"],"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/harnessing-the-power-of-mllms-for","slug":"harnessing-the-power-of-mllms-for","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","date":"2024-05-08","arxiv_id":"2405.04940","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/harnessing-the-power-of-mllms-for#ran","syntology_url":"https://syntology.ai/paper/2405.04940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04940"}},"official":{"repos":["wentaotan/mllm4text-reid"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-enhanced-machine","slug":"large-language-model-enhanced-machine","title":"Large Language Model Enhanced Machine Learning Estimators for Classification","date":"2024-05-08","arxiv_id":"2405.05445","repositories_listed":1,"syntology":null},{"url":"/paper/xampler-learning-to-retrieve-cross-lingual-in","slug":"xampler-learning-to-retrieve-cross-lingual-in","title":"XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples","date":"2024-05-08","arxiv_id":"2405.05116","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-knowledge-retrieval-with-topic","slug":"enhancing-knowledge-retrieval-with-topic","title":"Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue","date":"2024-05-07","arxiv_id":"2405.04713","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-adaptation-from-large-language","slug":"knowledge-adaptation-from-large-language","title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","date":"2024-05-07","arxiv_id":"2405.03988","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":1,"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/knowledge-adaptation-from-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.03988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03988"}},"official":{"repos":["adxcreative/LEARN"],"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/seed-data-edit-technical-report-a-hybrid","slug":"seed-data-edit-technical-report-a-hybrid","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","date":"2024-05-07","arxiv_id":"2405.04007","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/seed-data-edit-technical-report-a-hybrid#ran","syntology_url":"https://syntology.ai/paper/2405.04007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04007"}},"official":{"repos":["ailab-cvc/seed-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-fake-news-detection-with-large","slug":"explainable-fake-news-detection-with-large","title":"Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom","date":"2024-05-06","arxiv_id":"2405.03371","repositories_listed":1,"syntology":null},{"url":"/paper/mozart-s-touch-a-lightweight-multi-modal","slug":"mozart-s-touch-a-lightweight-multi-modal","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","date":"2024-05-05","arxiv_id":"2405.02801","repositories_listed":1,"syntology":null},{"url":"/paper/eda-corpus-a-large-language-model-dataset-for","slug":"eda-corpus-a-large-language-model-dataset-for","title":"EDA Corpus: A Large Language Model Dataset for Enhanced Interaction with OpenROAD","date":"2024-05-04","arxiv_id":"2405.06676","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-time-series-foundation-models","slug":"a-survey-of-time-series-foundation-models","title":"A Survey of Time Series Foundation Models: Generalizing Time Series Representation with Large Language Model","date":"2024-05-03","arxiv_id":"2405.02358","repositories_listed":1,"syntology":null},{"url":"/paper/dallmi-domain-adaption-for-llm-based-multi","slug":"dallmi-domain-adaption-for-llm-based-multi","title":"DALLMi: Domain Adaption for LLM-based Multi-label Classifier","date":"2024-05-03","arxiv_id":"2405.01883","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-chatgpt-for-diagnosing-autism","slug":"exploiting-chatgpt-for-diagnosing-autism","title":"Exploiting ChatGPT for Diagnosing Autism-Associated Language Disorders and Identifying Distinct Features","date":"2024-05-03","arxiv_id":"2405.01799","repositories_listed":1,"syntology":null},{"url":"/paper/llm-as-dataset-analyst-subpopulation","slug":"llm-as-dataset-analyst-subpopulation","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","date":"2024-05-03","arxiv_id":"2405.02363","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/llm-as-dataset-analyst-subpopulation#ran","syntology_url":"https://syntology.ai/paper/2405.02363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02363"}},"official":{"repos":["llm-as-dataset-analyst/SSDLLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/cos-enhancing-personalization-and-mitigating","slug":"cos-enhancing-personalization-and-mitigating","title":"CoS: Enhancing Personalization and Mitigating Bias with Context Steering","date":"2024-05-02","arxiv_id":"2405.01768","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/cos-enhancing-personalization-and-mitigating#ran","syntology_url":"https://syntology.ai/paper/2405.01768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01768"}},"official":{"repos":["sashrikap/context-steering"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-relevance-feedback-and-convergence","slug":"generative-relevance-feedback-and-convergence","title":"Generative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023","date":"2024-05-02","arxiv_id":"2405.01122","repositories_listed":1,"syntology":null},{"url":"/paper/biomedrag-a-retrieval-augmented-large","slug":"biomedrag-a-retrieval-augmented-large","title":"BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine","date":"2024-05-01","arxiv_id":"2405.00465","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/biomedrag-a-retrieval-augmented-large#ran","syntology_url":"https://syntology.ai/paper/2405.00465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00465"}},"official":{"repos":["toneli/petailor-for-bio-triple-extraction"],"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/distillation-matters-empowering-sequential","slug":"distillation-matters-empowering-sequential","title":"Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model","date":"2024-05-01","arxiv_id":"2405.00338","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/distillation-matters-empowering-sequential#ran","syntology_url":"https://syntology.ai/paper/2405.00338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00338"}},"official":{"repos":["istarryn/dllm2rec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/integrating-a-i-in-higher-education-protocol","slug":"integrating-a-i-in-higher-education-protocol","title":"Integrating A.I. in Higher Education: Protocol for a Pilot Study with 'SAMCares: An Adaptive Learning Hub'","date":"2024-05-01","arxiv_id":"2405.00330","repositories_listed":1,"syntology":null},{"url":"/paper/is-bigger-edit-batch-size-always-better-an","slug":"is-bigger-edit-batch-size-always-better-an","title":"Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3","date":"2024-05-01","arxiv_id":"2405.00664","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":2,"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/is-bigger-edit-batch-size-always-better-an#ran","syntology_url":"https://syntology.ai/paper/2405.00664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00664"}},"official":{"repos":["scalable-model-editing/unified-model-editing"],"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/tablevqa-bench-a-visual-question-answering","slug":"tablevqa-bench-a-visual-question-answering","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","date":"2024-04-30","arxiv_id":"2404.19205","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/tablevqa-bench-a-visual-question-answering#ran","syntology_url":"https://syntology.ai/paper/2404.19205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19205"}},"official":{"repos":["naver-ai/tablevqabench"],"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/human-in-the-loop-synthetic-text-data","slug":"human-in-the-loop-synthetic-text-data","title":"Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking","date":"2024-04-29","arxiv_id":"2404.18881","repositories_listed":1,"syntology":null},{"url":"/paper/cre-llm-a-domain-specific-chinese-relation","slug":"cre-llm-a-domain-specific-chinese-relation","title":"CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language Model","date":"2024-04-28","arxiv_id":"2404.18085","repositories_listed":1,"syntology":null},{"url":"/paper/paint-by-inpaint-learning-to-add-image","slug":"paint-by-inpaint-learning-to-add-image","title":"Paint by Inpaint: Learning to Add Image Objects by Removing Them First","date":"2024-04-28","arxiv_id":"2404.18212","repositories_listed":1,"syntology":null},{"url":"/paper/ranked-list-truncation-for-large-language","slug":"ranked-list-truncation-for-large-language","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","date":"2024-04-28","arxiv_id":"2404.18185","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"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) · 2 unverified","sample_list":"/paper/ranked-list-truncation-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.18185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18185"}},"official":{"repos":["chuanmeng/rlt4reranking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/worldgpt-empowering-llm-as-multimodal-world","slug":"worldgpt-empowering-llm-as-multimodal-world","title":"WorldGPT: Empowering LLM as Multimodal World Model","date":"2024-04-28","arxiv_id":"2404.18202","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/worldgpt-empowering-llm-as-multimodal-world#ran","syntology_url":"https://syntology.ai/paper/2404.18202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18202"}},"official":{"repos":["dcdmllm/worldgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/player-enhancing-llm-based-multi-agent","slug":"player-enhancing-llm-based-multi-agent","title":"PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games","date":"2024-04-26","arxiv_id":"2404.17662","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-class-membership-relations-in","slug":"evaluating-class-membership-relations-in","title":"Evaluating Class Membership Relations in Knowledge Graphs using Large Language Models","date":"2024-04-25","arxiv_id":"2404.17000","repositories_listed":1,"syntology":null},{"url":"/paper/how-far-are-we-to-gpt-4v-closing-the-gap-to","slug":"how-far-are-we-to-gpt-4v-closing-the-gap-to","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","date":"2024-04-25","arxiv_id":"2404.16821","repositories_listed":1,"syntology":null},{"url":"/paper/attacks-on-third-party-apis-of-large-language","slug":"attacks-on-third-party-apis-of-large-language","title":"Attacks on Third-Party APIs of Large Language Models","date":"2024-04-24","arxiv_id":"2404.16891","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/attacks-on-third-party-apis-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.16891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16891"}},"official":{"repos":["vk0812/third-party-attacks-on-llms"],"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/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/studying-large-language-model-behaviors-under","slug":"studying-large-language-model-behaviors-under","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","date":"2024-04-24","arxiv_id":"2404.16032","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":8,"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/studying-large-language-model-behaviors-under#ran","syntology_url":"https://syntology.ai/paper/2404.16032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16032"}},"official":{"repos":["kortukov/realistic_knowledge_conflicts"],"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/aligning-llm-agents-by-learning-latent","slug":"aligning-llm-agents-by-learning-latent","title":"Aligning LLM Agents by Learning Latent Preference from User Edits","date":"2024-04-23","arxiv_id":"2404.15269","repositories_listed":1,"syntology":null},{"url":"/paper/boter-bootstrapping-knowledge-selection-and","slug":"boter-bootstrapping-knowledge-selection-and","title":"Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering","date":"2024-04-22","arxiv_id":"2404.13947","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/boter-bootstrapping-knowledge-selection-and#ran","syntology_url":"https://syntology.ai/paper/2404.13947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13947"}},"official":{"repos":["haodongze/self-ksel-qans"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cofinal-enhancing-action-quality-assessment","slug":"cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","date":"2024-04-22","arxiv_id":"2404.13999","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cofinal-enhancing-action-quality-assessment#ran","syntology_url":"https://syntology.ai/paper/2404.13999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13999"}},"official":{"repos":["zhoukanglei/cofinal_aqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/melange-cost-efficient-large-language-model","slug":"melange-cost-efficient-large-language-model","title":"Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","date":"2024-04-22","arxiv_id":"2404.14527","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":2,"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/melange-cost-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2404.14527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14527"}},"official":{"repos":["tyler-griggs/melange-release"],"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/valor-eval-holistic-coverage-and-faithfulness","slug":"valor-eval-holistic-coverage-and-faithfulness","title":"VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models","date":"2024-04-22","arxiv_id":"2404.13874","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/valor-eval-holistic-coverage-and-faithfulness#ran","syntology_url":"https://syntology.ai/paper/2404.13874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13874"}},"official":{"repos":["haoyiq114/valor"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/a-survey-on-the-memory-mechanism-of-large","slug":"a-survey-on-the-memory-mechanism-of-large","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","date":"2024-04-21","arxiv_id":"2404.13501","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-retrieval-quality-in-retrieval","slug":"evaluating-retrieval-quality-in-retrieval","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","date":"2024-04-21","arxiv_id":"2404.13781","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/evaluating-retrieval-quality-in-retrieval#ran","syntology_url":"https://syntology.ai/paper/2404.13781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13781"}},"official":{"repos":["alirezasalemi7/erag"],"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/finerec-exploring-fine-grained-sequential","slug":"finerec-exploring-fine-grained-sequential","title":"FineRec:Exploring Fine-grained Sequential Recommendation","date":"2024-04-19","arxiv_id":"2404.12975","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/finerec-exploring-fine-grained-sequential#ran","syntology_url":"https://syntology.ai/paper/2404.12975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12975"}},"official":{"repos":["zhang-xiaokun/finerec"],"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/groma-localized-visual-tokenization-for","slug":"groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","date":"2024-04-19","arxiv_id":"2404.13013","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":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/groma-localized-visual-tokenization-for#ran","syntology_url":"https://syntology.ai/paper/2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"official":{"repos":["FoundationVision/Groma"],"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/llm-r2-a-large-language-model-enhanced-rule","slug":"llm-r2-a-large-language-model-enhanced-rule","title":"LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency","date":"2024-04-19","arxiv_id":"2404.12872","repositories_listed":1,"syntology":null},{"url":"/paper/mova-adapting-mixture-of-vision-experts-to","slug":"mova-adapting-mixture-of-vision-experts-to","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","date":"2024-04-19","arxiv_id":"2404.13046","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mova-adapting-mixture-of-vision-experts-to#ran","syntology_url":"https://syntology.ai/paper/2404.13046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13046"}},"official":{"repos":["templex98/mova"],"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","unlocated"]}}},{"url":"/paper/sos-1k-a-fine-grained-suicide-risk","slug":"sos-1k-a-fine-grained-suicide-risk","title":"SOS-1K: A Fine-grained Suicide Risk Classification Dataset for Chinese Social Media Analysis","date":"2024-04-19","arxiv_id":"2404.12659","repositories_listed":1,"syntology":null},{"url":"/paper/generating-diverse-criteria-on-the-fly-to","slug":"generating-diverse-criteria-on-the-fly-to","title":"MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers","date":"2024-04-18","arxiv_id":"2404.11960","repositories_listed":1,"syntology":null},{"url":"/paper/improving-composed-image-retrieval-via","slug":"improving-composed-image-retrieval-via","title":"Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives","date":"2024-04-17","arxiv_id":"2404.11317","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":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) · 1 unverified","sample_list":"/paper/improving-composed-image-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2404.11317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11317"}},"official":{"repos":["BUAADreamer/SPN4CIR"],"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/llmtune-accelerate-database-knob-tuning-with","slug":"llmtune-accelerate-database-knob-tuning-with","title":"E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model","date":"2024-04-17","arxiv_id":"2404.11581","repositories_listed":1,"syntology":null},{"url":"/paper/rd2bench-toward-data-centric-automatic-r-d","slug":"rd2bench-toward-data-centric-automatic-r-d","title":"Towards Data-Centric Automatic R&D","date":"2024-04-17","arxiv_id":"2404.11276","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-speciality-and-versatility-a-coarse","slug":"balancing-speciality-and-versatility-a-coarse","title":"Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model","date":"2024-04-16","arxiv_id":"2404.10306","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/balancing-speciality-and-versatility-a-coarse#ran","syntology_url":"https://syntology.ai/paper/2404.10306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10306"}},"official":{"repos":["rattlesnakey/cofitune"],"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/deep-learning-and-llm-based-methods-applied","slug":"deep-learning-and-llm-based-methods-applied","title":"Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification","date":"2024-04-16","arxiv_id":"2404.10757","repositories_listed":1,"syntology":null},{"url":"/paper/hlat-high-quality-large-language-model-pre","slug":"hlat-high-quality-large-language-model-pre","title":"HLAT: High-quality Large Language Model Pre-trained on AWS Trainium","date":"2024-04-16","arxiv_id":"2404.10630","repositories_listed":1,"syntology":null},{"url":"/paper/spiral-of-silences-how-is-large-language","slug":"spiral-of-silences-how-is-large-language","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10496","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-a-multilingual-large-language-model","slug":"teaching-a-multilingual-large-language-model","title":"Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training","date":"2024-04-16","arxiv_id":"2404.10922","repositories_listed":1,"syntology":null},{"url":"/paper/a-self-feedback-knowledge-elicitation","slug":"a-self-feedback-knowledge-elicitation","title":"A Self-feedback Knowledge Elicitation Approach for Chemical Reaction Predictions","date":"2024-04-15","arxiv_id":"2404.09606","repositories_listed":1,"syntology":null},{"url":"/paper/in2in-leveraging-individual-information-to-1","slug":"in2in-leveraging-individual-information-to-1","title":"in2IN: Leveraging individual Information to Generate Human INteractions","date":"2024-04-15","arxiv_id":"2404.09988","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/in2in-leveraging-individual-information-to-1#ran","syntology_url":"https://syntology.ai/paper/2404.09988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09988"}},"official":{"repos":["pabloruizponce/in2IN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-sharing-for-large-language-model-based","slug":"memory-sharing-for-large-language-model-based","title":"Memory Sharing for Large Language Model based Agents","date":"2024-04-15","arxiv_id":"2404.09982","repositories_listed":1,"syntology":null},{"url":"/paper/llmsat-a-large-language-model-based-goal","slug":"llmsat-a-large-language-model-based-goal","title":"LLMSat: A Large Language Model-Based Goal-Oriented Agent for Autonomous Space Exploration","date":"2024-04-13","arxiv_id":"2405.01392","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-autonomous-vehicle-training-with","slug":"enhancing-autonomous-vehicle-training-with","title":"Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation","date":"2024-04-12","arxiv_id":"2404.08570","repositories_listed":1,"syntology":null},{"url":"/paper/inverse-kinematics-for-neuro-robotic-grasping","slug":"inverse-kinematics-for-neuro-robotic-grasping","title":"Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents","date":"2024-04-12","arxiv_id":"2404.08825","repositories_listed":1,"syntology":null},{"url":"/paper/llm-seg-bridging-image-segmentation-and-large","slug":"llm-seg-bridging-image-segmentation-and-large","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","date":"2024-04-12","arxiv_id":"2404.08767","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/llm-seg-bridging-image-segmentation-and-large#ran","syntology_url":"https://syntology.ai/paper/2404.08767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08767"}},"official":{"repos":["wangjunchi/llmseg"],"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/ferret-v2-an-improved-baseline-for-referring","slug":"ferret-v2-an-improved-baseline-for-referring","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","date":"2024-04-11","arxiv_id":"2404.07973","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/ferret-v2-an-improved-baseline-for-referring#ran","syntology_url":"https://syntology.ai/paper/2404.07973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07973"}},"official":null}},{"url":"/paper/from-words-to-numbers-your-large-language","slug":"from-words-to-numbers-your-large-language","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","date":"2024-04-11","arxiv_id":"2404.07544","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":10,"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/from-words-to-numbers-your-large-language#ran","syntology_url":"https://syntology.ai/paper/2404.07544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07544"}},"official":{"repos":["robertvacareanu/llm4regression"],"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/lavy-vietnamese-multimodal-large-language","slug":"lavy-vietnamese-multimodal-large-language","title":"LaVy: Vietnamese Multimodal Large Language Model","date":"2024-04-11","arxiv_id":"2404.07922","repositories_listed":1,"syntology":null},{"url":"/paper/openbias-open-set-bias-detection-in-text-to","slug":"openbias-open-set-bias-detection-in-text-to","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","date":"2024-04-11","arxiv_id":"2404.07990","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openbias-open-set-bias-detection-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2404.07990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07990"}},"official":{"repos":["picsart-ai-research/openbias"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-language-model-with-generalized","slug":"scalable-language-model-with-generalized","title":"Scalable Language Model with Generalized Continual Learning","date":"2024-04-11","arxiv_id":"2404.07470","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":9,"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/scalable-language-model-with-generalized#ran","syntology_url":"https://syntology.ai/paper/2404.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07470"}},"official":{"repos":["pbihao/slm"],"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/learn-from-failure-fine-tuning-llms-with","slug":"learn-from-failure-fine-tuning-llms-with","title":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","date":"2024-04-10","arxiv_id":"2404.07382","repositories_listed":1,"syntology":null},{"url":"/paper/lossless-acceleration-of-large-language-model","slug":"lossless-acceleration-of-large-language-model","title":"Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding","date":"2024-04-10","arxiv_id":"2404.08698","repositories_listed":1,"syntology":null},{"url":"/paper/umbrae-unified-multimodal-decoding-of-brain","slug":"umbrae-unified-multimodal-decoding-of-brain","title":"UMBRAE: Unified Multimodal Brain Decoding","date":"2024-04-10","arxiv_id":"2404.07202","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/umbrae-unified-multimodal-decoding-of-brain#ran","syntology_url":"https://syntology.ai/paper/2404.07202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07202"}},"official":{"repos":["weihaox/UMBRAE"],"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/enhancing-decision-analysis-with-a-large","slug":"enhancing-decision-analysis-with-a-large","title":"Enhancing Decision Analysis with a Large Language Model: pyDecision a Comprehensive Library of MCDA Methods in Python","date":"2024-04-09","arxiv_id":"2404.06370","repositories_listed":1,"syntology":null},{"url":"/paper/freeeval-a-modular-framework-for-trustworthy","slug":"freeeval-a-modular-framework-for-trustworthy","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","date":"2024-04-09","arxiv_id":"2404.06003","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/freeeval-a-modular-framework-for-trustworthy#ran","syntology_url":"https://syntology.ai/paper/2404.06003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06003"}},"official":{"repos":["wisdomshell/freeeval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/360degrea-towards-a-reusable-experience","slug":"360degrea-towards-a-reusable-experience","title":"360$^\\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System","date":"2024-04-08","arxiv_id":"2404.05569","repositories_listed":1,"syntology":null},{"url":"/paper/have-you-merged-my-model-on-the-robustness-of","slug":"have-you-merged-my-model-on-the-robustness-of","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","date":"2024-04-08","arxiv_id":"2404.05188","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/have-you-merged-my-model-on-the-robustness-of#ran","syntology_url":"https://syntology.ai/paper/2404.05188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05188"}},"official":{"repos":["thuccslab/mergeguard"],"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/moma-multimodal-llm-adapter-for-fast","slug":"moma-multimodal-llm-adapter-for-fast","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","date":"2024-04-08","arxiv_id":"2404.05674","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/moma-multimodal-llm-adapter-for-fast#ran","syntology_url":"https://syntology.ai/paper/2404.05674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05674"}},"official":{"repos":["bytedance/MoMA"],"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/retrieval-augmented-open-vocabulary-object","slug":"retrieval-augmented-open-vocabulary-object","title":"Retrieval-Augmented Open-Vocabulary Object Detection","date":"2024-04-08","arxiv_id":"2404.05687","repositories_listed":1,"syntology":null},{"url":"/paper/safetyprompts-a-systematic-review-of-open","slug":"safetyprompts-a-systematic-review-of-open","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","date":"2024-04-08","arxiv_id":"2404.05399","repositories_listed":1,"syntology":null},{"url":"/paper/xiwu-a-basis-flexible-and-learnable-llm-for","slug":"xiwu-a-basis-flexible-and-learnable-llm-for","title":"Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics","date":"2024-04-08","arxiv_id":"2404.08001","repositories_listed":1,"syntology":null},{"url":"/paper/pairaug-what-can-augmented-image-text-pairs","slug":"pairaug-what-can-augmented-image-text-pairs","title":"PairAug: What Can Augmented Image-Text Pairs Do for Radiology?","date":"2024-04-07","arxiv_id":"2404.04960","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pairaug-what-can-augmented-image-text-pairs#ran","syntology_url":"https://syntology.ai/paper/2404.04960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04960"}},"official":{"repos":["ytongxie/pairaug"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/squeezeattention-2d-management-of-kv-cache-in","slug":"squeezeattention-2d-management-of-kv-cache-in","title":"SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget","date":"2024-04-07","arxiv_id":"2404.04793","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/squeezeattention-2d-management-of-kv-cache-in#ran","syntology_url":"https://syntology.ai/paper/2404.04793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04793"}},"official":{"repos":["hetailang/squeezeattention"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comparison-of-methods-for-evaluating","slug":"a-comparison-of-methods-for-evaluating","title":"A Comparison of Methods for Evaluating Generative IR","date":"2024-04-05","arxiv_id":"2404.04044","repositories_listed":1,"syntology":null},{"url":"/paper/physics-event-classification-using-large","slug":"physics-event-classification-using-large","title":"Physics Event Classification Using Large Language Models","date":"2024-04-05","arxiv_id":"2404.05752","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/physics-event-classification-using-large#ran","syntology_url":"https://syntology.ai/paper/2404.05752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05752"}},"official":{"repos":["ai4eic/ai4eichackathon2023-streamlit"],"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/autowebglm-bootstrap-and-reinforce-a-large","slug":"autowebglm-bootstrap-and-reinforce-a-large","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","date":"2024-04-04","arxiv_id":"2404.03648","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/autowebglm-bootstrap-and-reinforce-a-large#ran","syntology_url":"https://syntology.ai/paper/2404.03648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03648"}},"official":{"repos":["thudm/autowebglm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cbr-rag-case-based-reasoning-for-retrieval","slug":"cbr-rag-case-based-reasoning-for-retrieval","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","date":"2024-04-04","arxiv_id":"2404.04302","repositories_listed":1,"syntology":null},{"url":"/paper/conflare-conformal-large-language-model","slug":"conflare-conformal-large-language-model","title":"CONFLARE: CONFormal LArge language model REtrieval","date":"2024-04-04","arxiv_id":"2404.04287","repositories_listed":1,"syntology":null},{"url":"/paper/fpt-feature-prompt-tuning-for-few-shot","slug":"fpt-feature-prompt-tuning-for-few-shot","title":"FPT: Feature Prompt Tuning for Few-shot Readability Assessment","date":"2024-04-03","arxiv_id":"2404.02772","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-large-language-model-based-game","slug":"a-survey-on-large-language-model-based-game","title":"A Survey on Large Language Model-Based Game Agents","date":"2024-04-02","arxiv_id":"2404.02039","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-automated-distractor-generation-for","slug":"exploring-automated-distractor-generation-for","title":"Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models","date":"2024-04-02","arxiv_id":"2404.02124","repositories_listed":1,"syntology":null},{"url":"/paper/llms-in-the-loop-leveraging-large-language","slug":"llms-in-the-loop-leveraging-large-language","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","date":"2024-04-02","arxiv_id":"2404.02261","repositories_listed":1,"syntology":null},{"url":"/paper/m2sa-multimodal-and-multilingual-model-for","slug":"m2sa-multimodal-and-multilingual-model-for","title":"M2SA: Multimodal and Multilingual Model for Sentiment Analysis of Tweets","date":"2024-04-02","arxiv_id":"2404.01753","repositories_listed":1,"syntology":null},{"url":"/paper/self-organized-agents-a-llm-multi-agent","slug":"self-organized-agents-a-llm-multi-agent","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","date":"2024-04-02","arxiv_id":"2404.02183","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/self-organized-agents-a-llm-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2404.02183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02183"}},"official":{"repos":["tsukushiai/self-organized-agent"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/aragog-advanced-rag-output-grading","slug":"aragog-advanced-rag-output-grading","title":"ARAGOG: Advanced RAG Output Grading","date":"2024-04-01","arxiv_id":"2404.01037","repositories_listed":1,"syntology":null},{"url":"/paper/developing-safe-and-responsible-large","slug":"developing-safe-and-responsible-large","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","date":"2024-04-01","arxiv_id":"2404.01399","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/developing-safe-and-responsible-large#ran","syntology_url":"https://syntology.ai/paper/2404.01399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01399"}},"official":{"repos":["shainarazavi/safe-responsible-llm"],"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/direct-preference-optimization-of-video-large","slug":"direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","arxiv_id":"2404.01258","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-optimization-of-video-large#ran","syntology_url":"https://syntology.ai/paper/2404.01258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01258"}},"official":{"repos":["riflezhang/llava-hound-dpo"],"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/evalverse-unified-and-accessible-library-for","slug":"evalverse-unified-and-accessible-library-for","title":"Evalverse: Unified and Accessible Library for Large Language Model Evaluation","date":"2024-04-01","arxiv_id":"2404.00943","repositories_listed":1,"syntology":null},{"url":"/paper/learning-by-correction-efficient-tuning-task","slug":"learning-by-correction-efficient-tuning-task","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","date":"2024-04-01","arxiv_id":"2404.00909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-correction-efficient-tuning-task#ran","syntology_url":"https://syntology.ai/paper/2404.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00909"}},"official":{"repos":["shtuplus/iccc_cvpr2024"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lite-modeling-environmental-ecosystems-with","slug":"lite-modeling-environmental-ecosystems-with","title":"LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models","date":"2024-04-01","arxiv_id":"2404.01165","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/lite-modeling-environmental-ecosystems-with#ran","syntology_url":"https://syntology.ai/paper/2404.01165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01165"}},"official":{"repos":["hrlics/lite"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/query-performance-prediction-using-relevance","slug":"query-performance-prediction-using-relevance","title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","date":"2024-04-01","arxiv_id":"2404.01012","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":6,"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/query-performance-prediction-using-relevance#ran","syntology_url":"https://syntology.ai/paper/2404.01012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01012"}},"official":{"repos":["chuanmeng/qpp-genre"],"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"]}}}],"record_sha256":"b2eda0342d433b564cbed85a2efe385699b7596a04840014a604af738d97a701","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}