{"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/language-modelling/papers/36","list_of":"/task/language-modelling","task":"Language Modelling","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":36,"pages_in_order":177,"rows_per_page":100,"rows":[3501,3600],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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/language-modelling","prev":"/task/language-modelling/papers/35","next":"/task/language-modelling/papers/37","papers":[{"url":"/paper/multi-objective-differentiable-neural","slug":"multi-objective-differentiable-neural","title":"Multi-objective Differentiable Neural Architecture Search","date":"2024-02-28","arxiv_id":"2402.18213","repositories_listed":1,"syntology":null},{"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/synartifact-classifying-and-alleviating","slug":"synartifact-classifying-and-alleviating","title":"SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model","date":"2024-02-28","arxiv_id":"2402.18068","repositories_listed":1,"syntology":null},{"url":"/paper/trends-applications-and-challenges-in-human","slug":"trends-applications-and-challenges-in-human","title":"Trends, Applications, and Challenges in Human Attention Modelling","date":"2024-02-28","arxiv_id":"2402.18673","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-information-refinement-training","slug":"unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","arxiv_id":"2402.18150","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-information-refinement-training#ran","syntology_url":"https://syntology.ai/paper/2402.18150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18150"}},"official":{"repos":["xsc1234/info-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-language-model-based-framework-for-new","slug":"a-language-model-based-framework-for-new","title":"A Language Model based Framework for New Concept Placement in Ontologies","date":"2024-02-27","arxiv_id":"2402.17897","repositories_listed":1,"syntology":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/enhancing-efficiency-in-sparse-models-with","slug":"enhancing-efficiency-in-sparse-models-with","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","date":"2024-02-27","arxiv_id":"2403.18926","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-efficiency-in-sparse-models-with#ran","syntology_url":"https://syntology.ai/paper/2403.18926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18926"}},"official":{"repos":["ysngki/xmoe"],"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/large-language-models-on-tabular-data-a","slug":"large-language-models-on-tabular-data-a","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","date":"2024-02-27","arxiv_id":"2402.17944","repositories_listed":1,"syntology":null},{"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/nextlevelbert-investigating-masked-language","slug":"nextlevelbert-investigating-masked-language","title":"NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents","date":"2024-02-27","arxiv_id":"2402.17682","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/ravel-evaluating-interpretability-methods-on","slug":"ravel-evaluating-interpretability-methods-on","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","date":"2024-02-27","arxiv_id":"2402.17700","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":1,"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/ravel-evaluating-interpretability-methods-on#ran","syntology_url":"https://syntology.ai/paper/2402.17700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17700"}},"official":{"repos":["explanare/ravel"],"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/retrieval-is-accurate-generation","slug":"retrieval-is-accurate-generation","title":"Retrieval is Accurate Generation","date":"2024-02-27","arxiv_id":"2402.17532","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-is-accurate-generation#ran","syntology_url":"https://syntology.ai/paper/2402.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17532"}},"official":{"repos":["gmftbygmftby/copyisallyouneed"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","unlocated"]}}},{"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/stable-lm-2-1-6b-technical-report","slug":"stable-lm-2-1-6b-technical-report","title":"Stable LM 2 1.6B Technical Report","date":"2024-02-27","arxiv_id":"2402.17834","repositories_listed":1,"syntology":null},{"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/a-comprehensive-evaluation-of-quantization","slug":"a-comprehensive-evaluation-of-quantization","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","date":"2024-02-26","arxiv_id":"2402.16775","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"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) · 3 unverified","sample_list":"/paper/a-comprehensive-evaluation-of-quantization#ran","syntology_url":"https://syntology.ai/paper/2402.16775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16775"}},"official":{"repos":["cordercorder/quant_eval"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/codes-towards-building-open-source-language","slug":"codes-towards-building-open-source-language","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","date":"2024-02-26","arxiv_id":"2402.16347","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/codes-towards-building-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2402.16347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16347"}},"official":{"repos":["ruckbreasoning/codes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"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/long-context-language-modeling-with-parallel","slug":"long-context-language-modeling-with-parallel","title":"Long-Context Language Modeling with Parallel Context Encoding","date":"2024-02-26","arxiv_id":"2402.16617","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/long-context-language-modeling-with-parallel#ran","syntology_url":"https://syntology.ai/paper/2402.16617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16617"}},"official":{"repos":["princeton-nlp/cepe"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/pandora-s-white-box-increased-training-data","slug":"pandora-s-white-box-increased-training-data","title":"Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models","date":"2024-02-26","arxiv_id":"2402.17012","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/pandora-s-white-box-increased-training-data#ran","syntology_url":"https://syntology.ai/paper/2402.17012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17012"}},"official":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/graphwiz-an-instruction-following-language","slug":"graphwiz-an-instruction-following-language","title":"GraphWiz: An Instruction-Following Language Model for Graph Problems","date":"2024-02-25","arxiv_id":"2402.16029","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"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) · 2 unverified","sample_list":"/paper/graphwiz-an-instruction-following-language#ran","syntology_url":"https://syntology.ai/paper/2402.16029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16029"}},"official":{"repos":["nuochenpku/Graph-Reasoning-LLM"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/higpt-heterogeneous-graph-language-model","slug":"higpt-heterogeneous-graph-language-model","title":"HiGPT: Heterogeneous Graph Language Model","date":"2024-02-25","arxiv_id":"2402.16024","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/higpt-heterogeneous-graph-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.16024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16024"}},"official":{"repos":["hkuds/higpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/hypotermqa-hypothetical-terms-dataset-for","slug":"hypotermqa-hypothetical-terms-dataset-for","title":"HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs","date":"2024-02-25","arxiv_id":"2402.16211","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/say-more-with-less-understanding-prompt","slug":"say-more-with-less-understanding-prompt","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","date":"2024-02-25","arxiv_id":"2402.16058","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/say-more-with-less-understanding-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16058"}},"official":{"repos":["openmatch/gist-coco"],"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/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/substrate-prediction-for-ripp-biosynthetic","slug":"substrate-prediction-for-ripp-biosynthetic","title":"Substrate Prediction for RiPP Biosynthetic Enzymes via Masked Language Modeling and Transfer Learning","date":"2024-02-23","arxiv_id":"2402.15181","repositories_listed":1,"syntology":null},{"url":"/paper/the-good-and-the-bad-exploring-privacy-issues","slug":"the-good-and-the-bad-exploring-privacy-issues","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","date":"2024-02-23","arxiv_id":"2402.16893","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/the-good-and-the-bad-exploring-privacy-issues#ran","syntology_url":"https://syntology.ai/paper/2402.16893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16893"}},"official":{"repos":["phycholosogy/rag-privacy"],"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/balanced-data-sampling-for-language-model","slug":"balanced-data-sampling-for-language-model","title":"Balanced Data Sampling for Language Model Training with Clustering","date":"2024-02-22","arxiv_id":"2402.14526","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/balanced-data-sampling-for-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.14526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14526"}},"official":{"repos":["choosewhatulike/cluster-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cev-lm-controlled-edit-vector-language-model","slug":"cev-lm-controlled-edit-vector-language-model","title":"CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations","date":"2024-02-22","arxiv_id":"2402.14290","repositories_listed":1,"syntology":null},{"url":"/paper/cleaner-pretraining-corpus-curation-with","slug":"cleaner-pretraining-corpus-curation-with","title":"Cleaner Pretraining Corpus Curation with Neural Web Scraping","date":"2024-02-22","arxiv_id":"2402.14652","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleaner-pretraining-corpus-curation-with#ran","syntology_url":"https://syntology.ai/paper/2402.14652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14652"}},"official":{"repos":["openmatch/neuscraper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/instructir-a-benchmark-for-instruction","slug":"instructir-a-benchmark-for-instruction","title":"INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models","date":"2024-02-22","arxiv_id":"2402.14334","repositories_listed":1,"syntology":null},{"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/mitigating-fine-tuning-jailbreak-attack-with","slug":"mitigating-fine-tuning-jailbreak-attack-with","title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","date":"2024-02-22","arxiv_id":"2402.14968","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/q-probe-a-lightweight-approach-to-reward","slug":"q-probe-a-lightweight-approach-to-reward","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","date":"2024-02-22","arxiv_id":"2402.14688","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":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) · 0 unverified","sample_list":"/paper/q-probe-a-lightweight-approach-to-reward#ran","syntology_url":"https://syntology.ai/paper/2402.14688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14688"}},"official":{"repos":["likenneth/q_probe"],"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/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/uncertainty-aware-evaluation-for-vision","slug":"uncertainty-aware-evaluation-for-vision","title":"Uncertainty-Aware Evaluation for Vision-Language Models","date":"2024-02-22","arxiv_id":"2402.14418","repositories_listed":1,"syntology":{"n":17,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":7,"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, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/uncertainty-aware-evaluation-for-vision#ran","syntology_url":"https://syntology.ai/paper/2402.14418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14418"}},"official":{"repos":["ensec-ai/vlm-uncertainty-bench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/watermarking-makes-language-models","slug":"watermarking-makes-language-models","title":"Watermarking Makes Language Models Radioactive","date":"2024-02-22","arxiv_id":"2402.14904","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/watermarking-makes-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.14904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14904"}},"official":{"repos":["facebookresearch/radioactive-watermark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multimodal-in-context-tuning-approach-for-e","slug":"a-multimodal-in-context-tuning-approach-for-e","title":"A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation","date":"2024-02-21","arxiv_id":"2402.13587","repositories_listed":1,"syntology":null},{"url":"/paper/analysing-the-impact-of-sequence-composition","slug":"analysing-the-impact-of-sequence-composition","title":"Analysing The Impact of Sequence Composition on Language Model Pre-Training","date":"2024-02-21","arxiv_id":"2402.13991","repositories_listed":1,"syntology":{"n":21,"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analysing-the-impact-of-sequence-composition#ran","syntology_url":"https://syntology.ai/paper/2402.13991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13991"}},"official":{"repos":["yuzhaouoe/pretraining-data-packing"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"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/breaking-the-hisco-barrier-automatic","slug":"breaking-the-hisco-barrier-automatic","title":"Breaking the HISCO Barrier: Automatic Occupational Standardization with OccCANINE","date":"2024-02-21","arxiv_id":"2402.13604","repositories_listed":1,"syntology":null},{"url":"/paper/cognitive-visual-language-mapper-advancing","slug":"cognitive-visual-language-mapper-advancing","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","date":"2024-02-21","arxiv_id":"2402.13561","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cognitive-visual-language-mapper-advancing#ran","syntology_url":"https://syntology.ai/paper/2402.13561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13561"}},"official":{"repos":["hitsz-tmg/cognitive-visual-language-mapper"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/distillation-contrastive-decoding-improving","slug":"distillation-contrastive-decoding-improving","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","date":"2024-02-21","arxiv_id":"2402.14874","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/distillation-contrastive-decoding-improving#ran","syntology_url":"https://syntology.ai/paper/2402.14874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14874"}},"official":{"repos":["pphuc25/distil-cd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ed-copilot-reduce-emergency-department-wait","slug":"ed-copilot-reduce-emergency-department-wait","title":"ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance","date":"2024-02-21","arxiv_id":"2402.13448","repositories_listed":1,"syntology":null},{"url":"/paper/longwanjuan-towards-systematic-measurement","slug":"longwanjuan-towards-systematic-measurement","title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality","date":"2024-02-21","arxiv_id":"2402.13583","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longwanjuan-towards-systematic-measurement#ran","syntology_url":"https://syntology.ai/paper/2402.13583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13583"}},"official":{"repos":["openlmlab/longwanjuan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-social-biases-in-masked-language","slug":"measuring-social-biases-in-masked-language","title":"Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality","date":"2024-02-21","arxiv_id":"2402.13954","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/self-distillation-bridges-distribution-gap-in","slug":"self-distillation-bridges-distribution-gap-in","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","date":"2024-02-21","arxiv_id":"2402.13669","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":11,"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/self-distillation-bridges-distribution-gap-in#ran","syntology_url":"https://syntology.ai/paper/2402.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13669"}},"official":{"repos":["sail-sg/sdft"],"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/towards-building-multilingual-language-model","slug":"towards-building-multilingual-language-model","title":"Towards Building Multilingual Language Model for Medicine","date":"2024-02-21","arxiv_id":"2402.13963","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-building-multilingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13963"}},"official":{"repos":["magic-ai4med/mmedlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-but-effective-approach-to-improve-1","slug":"a-simple-but-effective-approach-to-improve-1","title":"A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction","date":"2024-02-20","arxiv_id":"2402.13364","repositories_listed":1,"syntology":null},{"url":"/paper/a-touch-vision-and-language-dataset-for","slug":"a-touch-vision-and-language-dataset-for","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","date":"2024-02-20","arxiv_id":"2402.13232","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-touch-vision-and-language-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2402.13232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13232"}},"official":{"repos":["Max-Fu/tvl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/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/arabicmmlu-assessing-massive-multitask","slug":"arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","date":"2024-02-20","arxiv_id":"2402.12840","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/arabicmmlu-assessing-massive-multitask#ran","syntology_url":"https://syntology.ai/paper/2402.12840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12840"}},"official":{"repos":["mbzuai-nlp/arabicmmlu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/gumbelsoft-diversified-language-model","slug":"gumbelsoft-diversified-language-model","title":"GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick","date":"2024-02-20","arxiv_id":"2402.12948","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gumbelsoft-diversified-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.12948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12948"}},"official":{"repos":["poruna-byte/gumbelsoft"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/heterogeneous-graph-reasoning-for-fact","slug":"heterogeneous-graph-reasoning-for-fact","title":"Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables","date":"2024-02-20","arxiv_id":"2402.13028","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/heterogeneous-graph-reasoning-for-fact#ran","syntology_url":"https://syntology.ai/paper/2402.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13028"}},"official":{"repos":["deno-v/heterfc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-do-hyenas-deal-with-human-speech-speech","slug":"how-do-hyenas-deal-with-human-speech-speech","title":"How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena","date":"2024-02-20","arxiv_id":"2402.13208","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-do-hyenas-deal-with-human-speech-speech#ran","syntology_url":"https://syntology.ai/paper/2402.13208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13208"}},"official":{"repos":["hlt-mt/fbk-fairseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/humaneval-on-latest-gpt-models-2024","slug":"humaneval-on-latest-gpt-models-2024","title":"HumanEval on Latest GPT Models -- 2024","date":"2024-02-20","arxiv_id":"2402.14852","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":1,"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/humaneval-on-latest-gpt-models-2024#ran","syntology_url":"https://syntology.ai/paper/2402.14852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14852"}},"official":{"repos":["daniel442li/gpt-human-eval"],"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/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/phonotactic-complexity-across-dialects","slug":"phonotactic-complexity-across-dialects","title":"Phonotactic Complexity across Dialects","date":"2024-02-20","arxiv_id":"2402.12998","repositories_listed":1,"syntology":null},{"url":"/paper/soft-self-consistency-improves-language-model","slug":"soft-self-consistency-improves-language-model","title":"Soft Self-Consistency Improves Language Model Agents","date":"2024-02-20","arxiv_id":"2402.13212","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soft-self-consistency-improves-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.13212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13212"}},"official":{"repos":["hannight/soft_self_consistency"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/text-guided-molecule-generation-with","slug":"text-guided-molecule-generation-with","title":"Text-Guided Molecule Generation with Diffusion Language Model","date":"2024-02-20","arxiv_id":"2402.13040","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":21,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/text-guided-molecule-generation-with#ran","syntology_url":"https://syntology.ai/paper/2402.13040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13040"}},"official":{"repos":["deno-v/tgm-dlm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/the-hidden-space-of-transformer-language","slug":"the-hidden-space-of-transformer-language","title":"The Hidden Space of Transformer Language Adapters","date":"2024-02-20","arxiv_id":"2402.13137","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/bayesian-parameter-efficient-fine-tuning-for","slug":"bayesian-parameter-efficient-fine-tuning-for","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","date":"2024-02-19","arxiv_id":"2402.12220","repositories_listed":1,"syntology":null},{"url":"/paper/codeart-better-code-models-by-attention","slug":"codeart-better-code-models-by-attention","title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","date":"2024-02-19","arxiv_id":"2402.11842","repositories_listed":1,"syntology":null},{"url":"/paper/compress-to-impress-unleashing-the-potential","slug":"compress-to-impress-unleashing-the-potential","title":"Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations","date":"2024-02-19","arxiv_id":"2402.11975","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/emulated-disalignment-safety-alignment-for","slug":"emulated-disalignment-safety-alignment-for","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","date":"2024-02-19","arxiv_id":"2402.12343","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/emulated-disalignment-safety-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2402.12343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12343"}},"official":{"repos":["ZHZisZZ/emulated-disalignment"],"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/language-model-adaptation-to-specialized","slug":"language-model-adaptation-to-specialized","title":"Language Model Adaptation to Specialized Domains through Selective Masking based on Genre and Topical Characteristics","date":"2024-02-19","arxiv_id":"2402.12036","repositories_listed":1,"syntology":null},{"url":"/paper/lemma-towards-lvlm-enhanced-multimodal","slug":"lemma-towards-lvlm-enhanced-multimodal","title":"LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation","date":"2024-02-19","arxiv_id":"2402.11943","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/lemma-towards-lvlm-enhanced-multimodal#ran","syntology_url":"https://syntology.ai/paper/2402.11943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11943"}},"official":{"repos":["fan19-hub/LEMMA"],"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/your-vision-language-model-itself-is-a-strong","slug":"your-vision-language-model-itself-is-a-strong","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","date":"2024-02-19","arxiv_id":"2402.12501","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/your-vision-language-model-itself-is-a-strong#ran","syntology_url":"https://syntology.ai/paper/2402.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12501"}},"official":{"repos":["rayruibochen/self-filter"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/allava-harnessing-gpt4v-synthesized-data-for","slug":"allava-harnessing-gpt4v-synthesized-data-for","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","date":"2024-02-18","arxiv_id":"2402.11684","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/allava-harnessing-gpt4v-synthesized-data-for#ran","syntology_url":"https://syntology.ai/paper/2402.11684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11684"}},"official":{"repos":["freedomintelligence/allava"],"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/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/integrating-pre-trained-language-model-with","slug":"integrating-pre-trained-language-model-with","title":"Integrating Pre-Trained Language Model with Physical Layer Communications","date":"2024-02-18","arxiv_id":"2402.11656","repositories_listed":1,"syntology":null},{"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/leia-facilitating-cross-lingual-knowledge","slug":"leia-facilitating-cross-lingual-knowledge","title":"LEIA: Facilitating Cross-lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation","date":"2024-02-18","arxiv_id":"2402.11485","repositories_listed":1,"syntology":null},{"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"]}}}],"record_sha256":"2ba2d5041a25b3785f87a09dc35096756dd5a41954fb2424381834491e0d8b00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}