{"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/17","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":17,"pages_in_order":61,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/task/large-language-model/papers/18","papers":[{"url":"/paper/lab-large-scale-alignment-for-chatbots","slug":"lab-large-scale-alignment-for-chatbots","title":"LAB: Large-Scale Alignment for ChatBots","date":"2024-03-02","arxiv_id":"2403.01081","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/lab-large-scale-alignment-for-chatbots#ran","syntology_url":"https://syntology.ai/paper/2403.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01081"}},"official":null}},{"url":"/paper/nomad-attention-efficient-llm-inference-on","slug":"nomad-attention-efficient-llm-inference-on","title":"NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention","date":"2024-03-02","arxiv_id":"2403.01273","repositories_listed":1,"syntology":null},{"url":"/paper/opengraph-towards-open-graph-foundation","slug":"opengraph-towards-open-graph-foundation","title":"OpenGraph: Towards Open Graph Foundation Models","date":"2024-03-02","arxiv_id":"2403.01121","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/opengraph-towards-open-graph-foundation#ran","syntology_url":"https://syntology.ai/paper/2403.01121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01121"}},"official":{"repos":["hkuds/opengraph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/softtiger-a-clinical-foundation-model-for","slug":"softtiger-a-clinical-foundation-model-for","title":"SoftTiger: A Clinical Foundation Model for Healthcare Workflows","date":"2024-03-01","arxiv_id":"2403.00868","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-reducing-catastrophic","slug":"analyzing-and-reducing-catastrophic","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","date":"2024-02-29","arxiv_id":"2402.18865","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"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) · 2 unverified","sample_list":"/paper/analyzing-and-reducing-catastrophic#ran","syntology_url":"https://syntology.ai/paper/2402.18865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18865"}},"official":{"repos":["which47/llmcl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-long-term-recommendation-with-bi","slug":"enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","arxiv_id":"2403.00843","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/enhancing-long-term-recommendation-with-bi#ran","syntology_url":"https://syntology.ai/paper/2403.00843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00843"}},"official":{"repos":["jizhi-zhang/billp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flexllm-a-system-for-co-serving-large","slug":"flexllm-a-system-for-co-serving-large","title":"FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning","date":"2024-02-29","arxiv_id":"2402.18789","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":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) · 3 unverified","sample_list":"/paper/flexllm-a-system-for-co-serving-large#ran","syntology_url":"https://syntology.ai/paper/2402.18789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18789"}},"official":{"repos":["flexflow/flexflow"],"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/generalizable-whole-slide-image","slug":"generalizable-whole-slide-image","title":"Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction","date":"2024-02-29","arxiv_id":"2402.19326","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":5,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 5 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/generalizable-whole-slide-image#ran","syntology_url":"https://syntology.ai/paper/2402.19326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19326"}},"official":{"repos":["ls1rius/wsi_five"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/characterizing-truthfulness-in-large-language","slug":"characterizing-truthfulness-in-large-language","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","date":"2024-02-28","arxiv_id":"2402.18048","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":5,"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/characterizing-truthfulness-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.18048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18048"}},"official":{"repos":["fanyin3639/lid-hallucinationdetection"],"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/cogbench-a-large-language-model-walks-into-a","slug":"cogbench-a-large-language-model-walks-into-a","title":"CogBench: a large language model walks into a psychology lab","date":"2024-02-28","arxiv_id":"2402.18225","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cogbench-a-large-language-model-walks-into-a#ran","syntology_url":"https://syntology.ai/paper/2402.18225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18225"}},"official":{"repos":["juliancodaforno/cogbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/data-interpreter-an-llm-agent-for-data","slug":"data-interpreter-an-llm-agent-for-data","title":"Data Interpreter: An LLM Agent For Data Science","date":"2024-02-28","arxiv_id":"2402.18679","repositories_listed":1,"syntology":null},{"url":"/paper/datasets-for-large-language-models-a","slug":"datasets-for-large-language-models-a","title":"Datasets for Large Language Models: A Comprehensive Survey","date":"2024-02-28","arxiv_id":"2402.18041","repositories_listed":1,"syntology":null},{"url":"/paper/grounding-language-models-for-visual-entity","slug":"grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","arxiv_id":"2402.18695","repositories_listed":1,"syntology":{"n":26,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/grounding-language-models-for-visual-entity#ran","syntology_url":"https://syntology.ai/paper/2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"official":{"repos":["mrzilinxiao/autover"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/prospect-personalized-recommendation-on-large","slug":"prospect-personalized-recommendation-on-large","title":"Prospect Personalized Recommendation on Large Language Model-based Agent Platform","date":"2024-02-28","arxiv_id":"2402.18240","repositories_listed":1,"syntology":null},{"url":"/paper/protllm-an-interleaved-protein-language-llm","slug":"protllm-an-interleaved-protein-language-llm","title":"ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training","date":"2024-02-28","arxiv_id":"2403.07920","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/protllm-an-interleaved-protein-language-llm#ran","syntology_url":"https://syntology.ai/paper/2403.07920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07920"}},"official":null}},{"url":"/paper/carzero-cross-attention-alignment-for","slug":"carzero-cross-attention-alignment-for","title":"CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification","date":"2024-02-27","arxiv_id":"2402.17417","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/carzero-cross-attention-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2402.17417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17417"}},"official":{"repos":["laihaoran/carzero"],"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/mathsensei-a-tool-augmented-large-language","slug":"mathsensei-a-tool-augmented-large-language","title":"MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning","date":"2024-02-27","arxiv_id":"2402.17231","repositories_listed":1,"syntology":null},{"url":"/paper/prediction-powered-ranking-of-large-language","slug":"prediction-powered-ranking-of-large-language","title":"Prediction-Powered Ranking of Large Language Models","date":"2024-02-27","arxiv_id":"2402.17826","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/prediction-powered-ranking-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17826"}},"official":{"repos":["networks-learning/prediction-powered-ranking"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/songcomposer-a-large-language-model-for-lyric","slug":"songcomposer-a-large-language-model-for-lyric","title":"SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition","date":"2024-02-27","arxiv_id":"2402.17645","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/songcomposer-a-large-language-model-for-lyric#ran","syntology_url":"https://syntology.ai/paper/2402.17645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17645"}},"official":{"repos":["pjlab-songcomposer/songcomposer"],"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/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-assisted-multi-teacher-continual-learning","slug":"llm-assisted-multi-teacher-continual-learning","title":"LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery","date":"2024-02-26","arxiv_id":"2402.16664","repositories_listed":1,"syntology":null},{"url":"/paper/mozip-a-multilingual-benchmark-to-evaluate","slug":"mozip-a-multilingual-benchmark-to-evaluate","title":"MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property","date":"2024-02-26","arxiv_id":"2402.16389","repositories_listed":1,"syntology":null},{"url":"/paper/mysterious-projections-multimodal-llms-gain","slug":"mysterious-projections-multimodal-llms-gain","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","date":"2024-02-26","arxiv_id":"2402.16832","repositories_listed":1,"syntology":null},{"url":"/paper/repoagent-an-llm-powered-open-source","slug":"repoagent-an-llm-powered-open-source","title":"RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation","date":"2024-02-26","arxiv_id":"2402.16667","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":2,"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/repoagent-an-llm-powered-open-source#ran","syntology_url":"https://syntology.ai/paper/2402.16667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16667"}},"official":{"repos":["openbmb/repoagent"],"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":["found_in_text","official"]}}},{"url":"/paper/retrieval-augmented-generation-systems","slug":"retrieval-augmented-generation-systems","title":"Retrieval Augmented Generation Systems: Automatic Dataset Creation, Evaluation and Boolean Agent Setup","date":"2024-02-26","arxiv_id":"2403.00820","repositories_listed":1,"syntology":null},{"url":"/paper/ldb-a-large-language-model-debugger-via","slug":"ldb-a-large-language-model-debugger-via","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","date":"2024-02-25","arxiv_id":"2402.16906","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":0,"n_no_contract":11,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/ldb-a-large-language-model-debugger-via#ran","syntology_url":"https://syntology.ai/paper/2402.16906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16906"}},"official":{"repos":["floridsleeves/llmdebugger"],"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/nesy-is-alive-and-well-a-llm-driven-symbolic","slug":"nesy-is-alive-and-well-a-llm-driven-symbolic","title":"NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification","date":"2024-02-25","arxiv_id":"2402.16910","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-large-language-model-agents","slug":"empowering-large-language-model-agents","title":"Empowering Large Language Model Agents through Action Learning","date":"2024-02-24","arxiv_id":"2402.15809","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/empowering-large-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2402.15809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15809"}},"official":{"repos":["zhao-ht/learnact"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/increasing-sam-zero-shot-performance-on","slug":"increasing-sam-zero-shot-performance-on","title":"TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation","date":"2024-02-24","arxiv_id":"2402.15759","repositories_listed":1,"syntology":null},{"url":"/paper/attributionbench-how-hard-is-automatic","slug":"attributionbench-how-hard-is-automatic","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","date":"2024-02-23","arxiv_id":"2402.15089","repositories_listed":1,"syntology":null},{"url":"/paper/item-side-fairness-of-large-language-model","slug":"item-side-fairness-of-large-language-model","title":"Item-side Fairness of Large Language Model-based Recommendation System","date":"2024-02-23","arxiv_id":"2402.15215","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/item-side-fairness-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.15215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15215"}},"official":{"repos":["jiangm-c/ifairlrs"],"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/megascale-scaling-large-language-model","slug":"megascale-scaling-large-language-model","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","date":"2024-02-23","arxiv_id":"2402.15627","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/megascale-scaling-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.15627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15627"}},"official":{"repos":["volcengine/vescale"],"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/llmbind-a-unified-modality-task-integration","slug":"llmbind-a-unified-modality-task-integration","title":"LLMBind: A Unified Modality-Task Integration Framework","date":"2024-02-22","arxiv_id":"2402.14891","repositories_listed":1,"syntology":null},{"url":"/paper/palo-a-polyglot-large-multimodal-model-for-5b","slug":"palo-a-polyglot-large-multimodal-model-for-5b","title":"PALO: A Polyglot Large Multimodal Model for 5B People","date":"2024-02-22","arxiv_id":"2402.14818","repositories_listed":1,"syntology":null},{"url":"/paper/relayattention-for-efficient-large-language","slug":"relayattention-for-efficient-large-language","title":"RelayAttention for Efficient Large Language Model Serving with Long System Prompts","date":"2024-02-22","arxiv_id":"2402.14808","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/relayattention-for-efficient-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.14808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14808"}},"official":{"repos":["rayleizhu/vllm-ra"],"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/simplot-enhancing-chart-question-answering-by","slug":"simplot-enhancing-chart-question-answering-by","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","date":"2024-02-22","arxiv_id":"2405.00021","repositories_listed":1,"syntology":null},{"url":"/paper/subobject-level-image-tokenization","slug":"subobject-level-image-tokenization","title":"Subobject-level Image Tokenization","date":"2024-02-22","arxiv_id":"2402.14327","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/subobject-level-image-tokenization#ran","syntology_url":"https://syntology.ai/paper/2402.14327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14327"}},"official":{"repos":["chendelong1999/subobjects"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenization-counts-the-impact-of","slug":"tokenization-counts-the-impact-of","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","date":"2024-02-22","arxiv_id":"2402.14903","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":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) · 1 unverified","sample_list":"/paper/tokenization-counts-the-impact-of#ran","syntology_url":"https://syntology.ai/paper/2402.14903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14903"}},"official":{"repos":["aadityasingh/tokenizationcounts"],"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/birco-a-benchmark-of-information-retrieval","slug":"birco-a-benchmark-of-information-retrieval","title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","date":"2024-02-21","arxiv_id":"2402.14151","repositories_listed":1,"syntology":null},{"url":"/paper/diet-odin-a-novel-framework-for-opioid-misuse","slug":"diet-odin-a-novel-framework-for-opioid-misuse","title":"Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns","date":"2024-02-21","arxiv_id":"2403.08820","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-preserving-instructions-for-aligning","slug":"privacy-preserving-instructions-for-aligning","title":"Privacy-Preserving Instructions for Aligning Large Language Models","date":"2024-02-21","arxiv_id":"2402.13659","repositories_listed":1,"syntology":null},{"url":"/paper/round-trip-translation-defence-against-large","slug":"round-trip-translation-defence-against-large","title":"Round Trip Translation Defence against Large Language Model Jailbreaking Attacks","date":"2024-02-21","arxiv_id":"2402.13517","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-taxonomy-guided-instruction-tuning","slug":"a-unified-taxonomy-guided-instruction-tuning","title":"A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion","date":"2024-02-20","arxiv_id":"2402.13405","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-prompting-in-context-learning-and","slug":"fine-tuning-prompting-in-context-learning-and","title":"Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance","date":"2024-02-20","arxiv_id":"2402.12819","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-tuned-language-models-are-better","slug":"instruction-tuned-language-models-are-better","title":"Instruction-tuned Language Models are Better Knowledge Learners","date":"2024-02-20","arxiv_id":"2402.12847","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-based-human-agent","slug":"large-language-model-based-human-agent","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","date":"2024-02-20","arxiv_id":"2402.12914","repositories_listed":1,"syntology":null},{"url":"/paper/mulan-multimodal-llm-agent-for-progressive","slug":"mulan-multimodal-llm-agent-for-progressive","title":"MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion","date":"2024-02-20","arxiv_id":"2402.12741","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-effects-of-language","slug":"understanding-the-effects-of-language","title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning","date":"2024-02-20","arxiv_id":"2402.13016","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/understanding-the-effects-of-language#ran","syntology_url":"https://syntology.ai/paper/2402.13016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13016"}},"official":{"repos":["idiap/class-imbalance-multilingual-ft"],"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/anygpt-unified-multimodal-llm-with-discrete","slug":"anygpt-unified-multimodal-llm-with-discrete","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","date":"2024-02-19","arxiv_id":"2402.12226","repositories_listed":1,"syntology":null},{"url":"/paper/direct-large-language-model-alignment-through","slug":"direct-large-language-model-alignment-through","title":"Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation","date":"2024-02-19","arxiv_id":"2402.11907","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/direct-large-language-model-alignment-through#ran","syntology_url":"https://syntology.ai/paper/2402.11907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11907"}},"official":{"repos":["exlaw/dlma"],"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/benchmarking-knowledge-boundary-for-large","slug":"benchmarking-knowledge-boundary-for-large","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","date":"2024-02-18","arxiv_id":"2402.11493","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/benchmarking-knowledge-boundary-for-large#ran","syntology_url":"https://syntology.ai/paper/2402.11493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11493"}},"official":{"repos":["pkulcwmzx/knowledge-boundary"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-driven-meta-structure","slug":"large-language-model-driven-meta-structure","title":"Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network","date":"2024-02-18","arxiv_id":"2402.11518","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"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) · 9 unverified","sample_list":"/paper/large-language-model-driven-meta-structure#ran","syntology_url":"https://syntology.ai/paper/2402.11518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11518"}},"official":{"repos":["linchen-65/restruct"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/momentor-advancing-video-large-language-model","slug":"momentor-advancing-video-large-language-model","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","date":"2024-02-18","arxiv_id":"2402.11435","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":1,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/momentor-advancing-video-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11435"}},"official":{"repos":["dcdmllm/momentor"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/preact-predicting-future-in-react-enhances","slug":"preact-predicting-future-in-react-enhances","title":"PreAct: Prediction Enhances Agent's Planning Ability","date":"2024-02-18","arxiv_id":"2402.11534","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/preact-predicting-future-in-react-enhances#ran","syntology_url":"https://syntology.ai/paper/2402.11534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11534"}},"official":{"repos":["fu-dayuan/preact"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stealthy-attack-on-large-language-model-based","slug":"stealthy-attack-on-large-language-model-based","title":"Stealthy Attack on Large Language Model based Recommendation","date":"2024-02-18","arxiv_id":"2402.14836","repositories_listed":1,"syntology":null},{"url":"/paper/collavo-crayon-large-language-and-vision","slug":"collavo-crayon-large-language-and-vision","title":"CoLLaVO: Crayon Large Language and Vision mOdel","date":"2024-02-17","arxiv_id":"2402.11248","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/collavo-crayon-large-language-and-vision#ran","syntology_url":"https://syntology.ai/paper/2402.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11248"}},"official":{"repos":["ByungKwanLee/CoLLaVO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/controlled-text-generation-for-large-language","slug":"controlled-text-generation-for-large-language","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","date":"2024-02-17","arxiv_id":"2402.11218","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-human-and-llm-preferences","slug":"dissecting-human-and-llm-preferences","title":"Dissecting Human and LLM Preferences","date":"2024-02-17","arxiv_id":"2402.11296","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/dissecting-human-and-llm-preferences#ran","syntology_url":"https://syntology.ai/paper/2402.11296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11296"}},"official":{"repos":["gair-nlp/preference-dissection"],"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/i-learn-better-if-you-speak-my-language","slug":"i-learn-better-if-you-speak-my-language","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","date":"2024-02-17","arxiv_id":"2402.11192","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":9,"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/i-learn-better-if-you-speak-my-language#ran","syntology_url":"https://syntology.ai/paper/2402.11192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11192"}},"official":{"repos":["xuanren4470/i-learn-better-if-you-speak-my-language"],"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/question-instructed-visual-descriptions-for","slug":"question-instructed-visual-descriptions-for","title":"Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering","date":"2024-02-16","arxiv_id":"2402.10698","repositories_listed":1,"syntology":null},{"url":"/paper/rag-driver-generalisable-driving-explanations","slug":"rag-driver-generalisable-driving-explanations","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","date":"2024-02-16","arxiv_id":"2402.10828","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":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) · 1 unverified","sample_list":"/paper/rag-driver-generalisable-driving-explanations#ran","syntology_url":"https://syntology.ai/paper/2402.10828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10828"}},"official":null}},{"url":"/paper/both-matter-enhancing-the-emotional","slug":"both-matter-enhancing-the-emotional","title":"Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence","date":"2024-02-15","arxiv_id":"2402.10073","repositories_listed":1,"syntology":null},{"url":"/paper/chemreasoner-heuristic-search-over-a-large","slug":"chemreasoner-heuristic-search-over-a-large","title":"ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback","date":"2024-02-15","arxiv_id":"2402.10980","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":7,"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/chemreasoner-heuristic-search-over-a-large#ran","syntology_url":"https://syntology.ai/paper/2402.10980","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10980"}},"official":{"repos":["pnnl/chemreasoner"],"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/optimus-scalable-optimization-modeling-with","slug":"optimus-scalable-optimization-modeling-with","title":"OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models","date":"2024-02-15","arxiv_id":"2402.10172","repositories_listed":1,"syntology":null},{"url":"/paper/self-augmented-in-context-learning-for","slug":"self-augmented-in-context-learning-for","title":"Self-Augmented In-Context Learning for Unsupervised Word Translation","date":"2024-02-15","arxiv_id":"2402.10024","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-augmented-in-context-learning-for#ran","syntology_url":"https://syntology.ai/paper/2402.10024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10024"}},"official":{"repos":["cambridgeltl/sail-bli"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rapid-adoption-hidden-risks-the-dual-impact","slug":"rapid-adoption-hidden-risks-the-dual-impact","title":"Instruction Backdoor Attacks Against Customized LLMs","date":"2024-02-14","arxiv_id":"2402.09179","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/rapid-adoption-hidden-risks-the-dual-impact#ran","syntology_url":"https://syntology.ai/paper/2402.09179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09179"}},"official":{"repos":["zhangrui4041/instruction_backdoor_attack"],"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/agent-smith-a-single-image-can-jailbreak-one","slug":"agent-smith-a-single-image-can-jailbreak-one","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","date":"2024-02-13","arxiv_id":"2402.08567","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":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) · 1 unverified","sample_list":"/paper/agent-smith-a-single-image-can-jailbreak-one#ran","syntology_url":"https://syntology.ai/paper/2402.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08567"}},"official":{"repos":["sail-sg/agent-smith"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prompt-optimization-in-multi-step-tasks#ran","syntology_url":"https://syntology.ai/paper/2402.08702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08702"}},"official":{"repos":["yongchao98/promst"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/punctuation-restoration-improves-structure","slug":"punctuation-restoration-improves-structure","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","date":"2024-02-13","arxiv_id":"2402.08382","repositories_listed":1,"syntology":null},{"url":"/paper/verified-multi-step-synthesis-using-large","slug":"verified-multi-step-synthesis-using-large","title":"VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Search","date":"2024-02-13","arxiv_id":"2402.08147","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/verified-multi-step-synthesis-using-large#ran","syntology_url":"https://syntology.ai/paper/2402.08147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08147"}},"official":{"repos":["namin/llm-verified-with-monte-carlo-tree-search"],"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/breakgpt-a-large-language-model-with-multi","slug":"breakgpt-a-large-language-model-with-multi","title":"BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection","date":"2024-02-12","arxiv_id":"2402.07536","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-the-clinical-features-of-difficult","slug":"detecting-the-clinical-features-of-difficult","title":"Detecting the Clinical Features of Difficult-to-Treat Depression using Synthetic Data from Large Language Models","date":"2024-02-12","arxiv_id":"2402.07645","repositories_listed":1,"syntology":null},{"url":"/paper/wildfiregpt-tailored-large-language-model-for","slug":"wildfiregpt-tailored-large-language-model-for","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","date":"2024-02-12","arxiv_id":"2402.07877","repositories_listed":1,"syntology":null},{"url":"/paper/graphtranslator-aligning-graph-model-to-large","slug":"graphtranslator-aligning-graph-model-to-large","title":"GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks","date":"2024-02-11","arxiv_id":"2402.07197","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graphtranslator-aligning-graph-model-to-large#ran","syntology_url":"https://syntology.ai/paper/2402.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07197"}},"official":{"repos":["alibaba/graphtranslator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/using-large-language-models-for-student-code","slug":"using-large-language-models-for-student-code","title":"Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education","date":"2024-02-11","arxiv_id":"2402.07081","repositories_listed":1,"syntology":null},{"url":"/paper/chemllm-a-chemical-large-language-model","slug":"chemllm-a-chemical-large-language-model","title":"ChemLLM: A Chemical Large Language Model","date":"2024-02-10","arxiv_id":"2402.06852","repositories_listed":1,"syntology":null},{"url":"/paper/urbankgent-a-unified-large-language-model","slug":"urbankgent-a-unified-large-language-model","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","date":"2024-02-10","arxiv_id":"2402.06861","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/urbankgent-a-unified-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.06861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06861"}},"official":{"repos":["usail-hkust/urbankgent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/aya-dataset-an-open-access-collection-for","slug":"aya-dataset-an-open-access-collection-for","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","date":"2024-02-09","arxiv_id":"2402.06619","repositories_listed":1,"syntology":null},{"url":"/paper/g-sciedbert-a-contextualized-llm-for-science","slug":"g-sciedbert-a-contextualized-llm-for-science","title":"G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German","date":"2024-02-09","arxiv_id":"2402.06584","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-sentence-completion-with-a","slug":"language-model-sentence-completion-with-a","title":"Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method","date":"2024-02-09","arxiv_id":"2402.06125","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-model-sentence-completion-with-a#ran","syntology_url":"https://syntology.ai/paper/2402.06125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06125"}},"official":{"repos":["joshua-zingale/plug-and-play-rst-ctg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"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/the-quantified-boolean-bayesian-network","slug":"the-quantified-boolean-bayesian-network","title":"The Quantified Boolean Bayesian Network: Theory and Experiments with a Logical Graphical Model","date":"2024-02-09","arxiv_id":"2402.06557","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-weakness-of-large-language","slug":"understanding-the-weakness-of-large-language","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","date":"2024-02-09","arxiv_id":"2402.06596","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/understanding-the-weakness-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.06596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06596"}},"official":{"repos":["androidarenaagent/androidarena"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/editable-scene-simulation-for-autonomous","slug":"editable-scene-simulation-for-autonomous","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","date":"2024-02-08","arxiv_id":"2402.05746","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/editable-scene-simulation-for-autonomous#ran","syntology_url":"https://syntology.ai/paper/2402.05746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05746"}},"official":{"repos":["yifanlu0227/chatsim"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sphinx-x-scaling-data-and-parameters-for-a","slug":"sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","arxiv_id":"2402.05935","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/sphinx-x-scaling-data-and-parameters-for-a#ran","syntology_url":"https://syntology.ai/paper/2402.05935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05935"}},"official":{"repos":["alpha-vllm/llama2-accessory"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/apiq-finetuning-of-2-bit-quantized-large","slug":"apiq-finetuning-of-2-bit-quantized-large","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","date":"2024-02-07","arxiv_id":"2402.05147","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":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) · 1 unverified","sample_list":"/paper/apiq-finetuning-of-2-bit-quantized-large#ran","syntology_url":"https://syntology.ai/paper/2402.05147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05147"}},"official":{"repos":["baohaoliao/apiq"],"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/can-large-language-model-agents-simulate","slug":"can-large-language-model-agents-simulate","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","date":"2024-02-07","arxiv_id":"2402.04559","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/can-large-language-model-agents-simulate#ran","syntology_url":"https://syntology.ai/paper/2402.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04559"}},"official":{"repos":["camel-ai/agent-trust"],"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/leveraging-llms-for-unsupervised-dense","slug":"leveraging-llms-for-unsupervised-dense","title":"Leveraging LLMs for Unsupervised Dense Retriever Ranking","date":"2024-02-07","arxiv_id":"2402.04853","repositories_listed":1,"syntology":null},{"url":"/paper/sumrec-a-framework-for-recommendation-using","slug":"sumrec-a-framework-for-recommendation-using","title":"SumRec: A Framework for Recommendation using Open-Domain Dialogue","date":"2024-02-07","arxiv_id":"2402.04523","repositories_listed":1,"syntology":null},{"url":"/paper/anytool-self-reflective-hierarchical-agents","slug":"anytool-self-reflective-hierarchical-agents","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","date":"2024-02-06","arxiv_id":"2402.04253","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/anytool-self-reflective-hierarchical-agents#ran","syntology_url":"https://syntology.ai/paper/2402.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04253"}},"official":{"repos":["dyabel/anytool"],"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/identifying-reasons-for-contraceptive","slug":"identifying-reasons-for-contraceptive","title":"Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models","date":"2024-02-06","arxiv_id":"2402.03597","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-distilling-medication","slug":"large-language-model-distilling-medication","title":"Large Language Model Distilling Medication Recommendation Model","date":"2024-02-05","arxiv_id":"2402.02803","repositories_listed":1,"syntology":null},{"url":"/paper/racer-an-llm-powered-methodology-for-scalable","slug":"racer-an-llm-powered-methodology-for-scalable","title":"RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews","date":"2024-02-05","arxiv_id":"2402.02656","repositories_listed":1,"syntology":null},{"url":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":18,"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) · 5 unverified","sample_list":"/paper/gerea-question-aware-prompt-captions-for#ran","syntology_url":"https://syntology.ai/paper/2402.02503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02503"}},"official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/glape-gold-label-agnostic-prompt-evaluation","slug":"glape-gold-label-agnostic-prompt-evaluation","title":"GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model","date":"2024-02-04","arxiv_id":"2402.02408","repositories_listed":1,"syntology":null},{"url":"/paper/kicgpt-large-language-model-with-knowledge-in","slug":"kicgpt-large-language-model-with-knowledge-in","title":"KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion","date":"2024-02-04","arxiv_id":"2402.02389","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kicgpt-large-language-model-with-knowledge-in#ran","syntology_url":"https://syntology.ai/paper/2402.02389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02389"}},"official":{"repos":["weiyanbin1999/kicgpt"],"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","unlocated"]}}},{"url":"/paper/selecting-large-language-model-to-fine-tune","slug":"selecting-large-language-model-to-fine-tune","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","date":"2024-02-04","arxiv_id":"2402.02314","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selecting-large-language-model-to-fine-tune#ran","syntology_url":"https://syntology.ai/paper/2402.02314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02314"}},"official":null}},{"url":"/paper/apiserve-efficient-api-support-for-large","slug":"apiserve-efficient-api-support-for-large","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","date":"2024-02-02","arxiv_id":"2402.01869","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/apiserve-efficient-api-support-for-large#ran","syntology_url":"https://syntology.ai/paper/2402.01869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01869"}},"official":{"repos":["wuklab/infercept"],"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/magdi-structured-distillation-of-multi-agent","slug":"magdi-structured-distillation-of-multi-agent","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","date":"2024-02-02","arxiv_id":"2402.01620","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/magdi-structured-distillation-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2402.01620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01620"}},"official":{"repos":["dinobby/magdi"],"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":"22d71498a5d347ea32f720ee99d972c5132237b0ec8302c7a0d93fbeacf88a67","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}