{"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-modeling/papers/ran/9","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":9,"pages_in_order":19,"rows_per_page":100,"rows":[801,900],"of":1894,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling/papers/ran/1","prev":"/task/language-modeling/papers/ran/8","next":"/task/language-modeling/papers/ran/10","papers":[{"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/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/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/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/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/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/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/repetition-improves-language-model-embeddings","slug":"repetition-improves-language-model-embeddings","title":"Repetition Improves Language Model Embeddings","date":"2024-02-23","arxiv_id":"2402.15449","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/repetition-improves-language-model-embeddings#ran","syntology_url":"https://syntology.ai/paper/2402.15449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15449"}},"official":{"repos":["jakespringer/echo-embeddings"],"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":["listed","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/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/self-retrieval-building-an-information","slug":"self-retrieval-building-an-information","title":"Self-Retrieval: End-to-End Information Retrieval with One Large Language Model","date":"2024-02-23","arxiv_id":"2403.00801","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-retrieval-building-an-information#ran","syntology_url":"https://syntology.ai/paper/2403.00801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00801"}},"official":{"repos":["icip-cas/selfretrieval","tangqiaoyu/selfretrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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/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/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/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/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/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/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/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/backward-lens-projecting-language-model","slug":"backward-lens-projecting-language-model","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","date":"2024-02-20","arxiv_id":"2402.12865","repositories_listed":0,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/backward-lens-projecting-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.12865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12865"}},"official":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/trap-targeted-random-adversarial-prompt","slug":"trap-targeted-random-adversarial-prompt","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","date":"2024-02-20","arxiv_id":"2402.12991","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trap-targeted-random-adversarial-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.12991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12991"}},"official":{"repos":["framartin/trap","parameterlab/trap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/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/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/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/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/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/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/generation-meets-verification-accelerating","slug":"generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","arxiv_id":"2402.11809","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generation-meets-verification-accelerating#ran","syntology_url":"https://syntology.ai/paper/2402.11809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11809"}},"official":{"repos":["cteant/space","hiyouga/llama-factory"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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/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/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/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/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/zerog-investigating-cross-dataset-zero-shot","slug":"zerog-investigating-cross-dataset-zero-shot","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","date":"2024-02-17","arxiv_id":"2402.11235","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zerog-investigating-cross-dataset-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2402.11235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11235"}},"official":{"repos":["nineabyss/zerog"],"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/linear-transformers-with-learnable-kernel","slug":"linear-transformers-with-learnable-kernel","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","date":"2024-02-16","arxiv_id":"2402.10644","repositories_listed":2,"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/linear-transformers-with-learnable-kernel#ran","syntology_url":"https://syntology.ai/paper/2402.10644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10644"}},"official":{"repos":["sustcsonglin/flash-linear-attention","corl-team/rebased"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-study-on-cross-lingual","slug":"an-empirical-study-on-cross-lingual","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","date":"2024-02-16","arxiv_id":"2402.10712","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":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) · 1 unverified","sample_list":"/paper/an-empirical-study-on-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/2402.10712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10712"}},"official":{"repos":["gucci-j/llm-cva"],"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/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/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/generative-representational-instruction","slug":"generative-representational-instruction","title":"Generative Representational Instruction Tuning","date":"2024-02-15","arxiv_id":"2402.09906","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"10 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-representational-instruction#ran","syntology_url":"https://syntology.ai/paper/2402.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09906"}},"official":{"repos":["contextualai/gritlm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/de-cop-detecting-copyrighted-content-in","slug":"de-cop-detecting-copyrighted-content-in","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","date":"2024-02-15","arxiv_id":"2402.09910","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/de-cop-detecting-copyrighted-content-in#ran","syntology_url":"https://syntology.ai/paper/2402.09910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09910"}},"official":{"repos":["avduarte333/de-cop_method","leililab/de-cop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/tell-me-more-towards-implicit-user-intention","slug":"tell-me-more-towards-implicit-user-intention","title":"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents","date":"2024-02-14","arxiv_id":"2402.09205","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tell-me-more-towards-implicit-user-intention#ran","syntology_url":"https://syntology.ai/paper/2402.09205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09205"}},"official":{"repos":["hbx-hbx/mistral-interact"],"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/scaling-the-authoring-of-autotutors-with","slug":"scaling-the-authoring-of-autotutors-with","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","date":"2024-02-14","arxiv_id":"2402.09216","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 6 unverified","sample_list":"/paper/scaling-the-authoring-of-autotutors-with#ran","syntology_url":"https://syntology.ai/paper/2402.09216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09216"}},"official":{"repos":["eth-lre/mwptutor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"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/measuring-and-controlling-instruction-in","slug":"measuring-and-controlling-instruction-in","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","date":"2024-02-13","arxiv_id":"2402.10962","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":5,"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/measuring-and-controlling-instruction-in#ran","syntology_url":"https://syntology.ai/paper/2402.10962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10962"}},"official":{"repos":["likenneth/persona_drift"],"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/automathtext-autonomous-data-selection-with","slug":"automathtext-autonomous-data-selection-with","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","date":"2024-02-12","arxiv_id":"2402.07625","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automathtext-autonomous-data-selection-with#ran","syntology_url":"https://syntology.ai/paper/2402.07625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07625"}},"official":{"repos":["hiyouga/llama-factory","yifanzhang-pro/automathtext"],"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/diffusion-of-thoughts-chain-of-thought","slug":"diffusion-of-thoughts-chain-of-thought","title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","date":"2024-02-12","arxiv_id":"2402.07754","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-of-thoughts-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2402.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07754"}},"official":{"repos":["hkunlp/diffusion-of-thoughts"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/open-ended-vqa-benchmarking-of-vision","slug":"open-ended-vqa-benchmarking-of-vision","title":"Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy","date":"2024-02-11","arxiv_id":"2402.07270","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/open-ended-vqa-benchmarking-of-vision#ran","syntology_url":"https://syntology.ai/paper/2402.07270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07270"}},"official":{"repos":["lmb-freiburg/ovqa"],"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/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/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/on-the-efficacy-of-eviction-policy-for-key","slug":"on-the-efficacy-of-eviction-policy-for-key","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","date":"2024-02-09","arxiv_id":"2402.06262","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-efficacy-of-eviction-policy-for-key#ran","syntology_url":"https://syntology.ai/paper/2402.06262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06262"}},"official":{"repos":["drsy/easykv"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/entropy-regularized-token-level-policy","slug":"entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","arxiv_id":"2402.06700","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entropy-regularized-token-level-policy#ran","syntology_url":"https://syntology.ai/paper/2402.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06700"}},"official":{"repos":["morning9393/etpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/screenagent-a-vision-language-model-driven","slug":"screenagent-a-vision-language-model-driven","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","date":"2024-02-09","arxiv_id":"2402.07945","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/screenagent-a-vision-language-model-driven#ran","syntology_url":"https://syntology.ai/paper/2402.07945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07945"}},"official":{"repos":["niuzaisheng/screenagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-graphs-meet-multi-modal-learning-a","slug":"knowledge-graphs-meet-multi-modal-learning-a","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","date":"2024-02-08","arxiv_id":"2402.05391","repositories_listed":6,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":4,"phrase":"15 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledge-graphs-meet-multi-modal-learning-a#ran","syntology_url":"https://syntology.ai/paper/2402.05391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05391"}},"official":{"repos":["zjukg/kg-mm-survey"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/spirit-lm-interleaved-spoken-and-written","slug":"spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","arxiv_id":"2402.05755","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/spirit-lm-interleaved-spoken-and-written#ran","syntology_url":"https://syntology.ai/paper/2402.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05755"}},"official":{"repos":["facebookresearch/spiritlm"],"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/how-do-transformers-perform-in-context","slug":"how-do-transformers-perform-in-context","title":"How do Transformers perform In-Context Autoregressive Learning?","date":"2024-02-08","arxiv_id":"2402.05787","repositories_listed":0,"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/how-do-transformers-perform-in-context#ran","syntology_url":"https://syntology.ai/paper/2402.05787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05787"}},"official":null}},{"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/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/codeit-self-improving-language-models-with","slug":"codeit-self-improving-language-models-with","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","date":"2024-02-07","arxiv_id":"2402.04858","repositories_listed":1,"syntology":{"n":41,"n_ran":32,"n_constructed":4,"n_ran_checked":10,"n_instrument":22,"n_unverified":9,"n_honours":4,"n_violates":2,"n_no_contract":4,"n_pointer_only":41,"phrase":"32 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 2 violated, 4 with no contract checked; 22 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/codeit-self-improving-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2402.04858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04858"}},"official":{"repos":["Qualcomm-AI-research/codeit"],"state":"official (archive's flag): 32 ran","n_ran":32,"n_constructed":4,"n_ran_no_instrument_failure":10,"n_unverified":9,"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/2402-03766","slug":"2402-03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","date":"2024-02-06","arxiv_id":"2402.03766","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2402-03766#ran","syntology_url":"https://syntology.ai/paper/2402.03766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03766"}},"official":{"repos":["meituan-automl/mobilevlm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-mamba-learn-how-to-learn-a-comparative","slug":"can-mamba-learn-how-to-learn-a-comparative","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","date":"2024-02-06","arxiv_id":"2402.04248","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-mamba-learn-how-to-learn-a-comparative#ran","syntology_url":"https://syntology.ai/paper/2402.04248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04248"}},"official":{"repos":["krafton-ai/mambaformer-icl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/personalized-language-modeling-from","slug":"personalized-language-modeling-from","title":"Personalized Language Modeling from Personalized Human Feedback","date":"2024-02-06","arxiv_id":"2402.05133","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/personalized-language-modeling-from#ran","syntology_url":"https://syntology.ai/paper/2402.05133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05133"}},"official":{"repos":["humainlab/personalized_rlhf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","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/skill-set-optimization-reinforcing-language#ran","syntology_url":"https://syntology.ai/paper/2402.03244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03244"}},"official":{"repos":["allenai/sso"],"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/jailbreaking-attack-against-multimodal-large","slug":"jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","arxiv_id":"2402.02309","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jailbreaking-attack-against-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02309"}},"official":{"repos":["abc03570128/jailbreaking-attack-against-multimodal-large-language-model"],"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":["listed","official"]}}},{"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/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/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/lhrs-bot-empowering-remote-sensing-with-vgi","slug":"lhrs-bot-empowering-remote-sensing-with-vgi","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","date":"2024-02-04","arxiv_id":"2402.02544","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lhrs-bot-empowering-remote-sensing-with-vgi#ran","syntology_url":"https://syntology.ai/paper/2402.02544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02544"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/decoding-speculative-decoding","slug":"decoding-speculative-decoding","title":"Decoding Speculative Decoding","date":"2024-02-02","arxiv_id":"2402.01528","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/decoding-speculative-decoding#ran","syntology_url":"https://syntology.ai/paper/2402.01528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01528"}},"official":{"repos":["uw-mad-dash/decoding-speculative-decoding"],"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/style-vectors-for-steering-generative-large","slug":"style-vectors-for-steering-generative-large","title":"Style Vectors for Steering Generative Large Language Model","date":"2024-02-02","arxiv_id":"2402.01618","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/style-vectors-for-steering-generative-large#ran","syntology_url":"https://syntology.ai/paper/2402.01618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01618"}},"official":{"repos":["dlr-sc/style-vectors-for-steering-llms"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/audio-flamingo-a-novel-audio-language-model","slug":"audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","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":3,"n_no_contract":0,"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, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}},"official":{"repos":["NVIDIA/audio-flamingo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/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/natural-language-guidance-of-high-fidelity","slug":"natural-language-guidance-of-high-fidelity","title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","date":"2024-02-02","arxiv_id":"2402.01912","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/natural-language-guidance-of-high-fidelity#ran","syntology_url":"https://syntology.ai/paper/2402.01912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01912"}},"official":null}},{"url":"/paper/superfiltering-weak-to-strong-data-filtering","slug":"superfiltering-weak-to-strong-data-filtering","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","date":"2024-02-01","arxiv_id":"2402.00530","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/superfiltering-weak-to-strong-data-filtering#ran","syntology_url":"https://syntology.ai/paper/2402.00530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00530"}},"official":{"repos":["tianyi-lab/superfiltering"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/non-exchangeable-conformal-language","slug":"non-exchangeable-conformal-language","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","date":"2024-02-01","arxiv_id":"2402.00707","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/non-exchangeable-conformal-language#ran","syntology_url":"https://syntology.ai/paper/2402.00707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00707"}},"official":{"repos":["kaleidophon/non-exchangeable-conformal-language-generation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/croissantllm-a-truly-bilingual-french-english","slug":"croissantllm-a-truly-bilingual-french-english","title":"CroissantLLM: A Truly Bilingual French-English Language Model","date":"2024-02-01","arxiv_id":"2402.00786","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/croissantllm-a-truly-bilingual-french-english#ran","syntology_url":"https://syntology.ai/paper/2402.00786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00786"}},"official":{"repos":["manuelfay/llm-data-hub"],"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/llms-learn-governing-principles-of-dynamical","slug":"llms-learn-governing-principles-of-dynamical","title":"LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law","date":"2024-02-01","arxiv_id":"2402.00795","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":2,"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/llms-learn-governing-principles-of-dynamical#ran","syntology_url":"https://syntology.ai/paper/2402.00795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00795"}},"official":{"repos":["AntonioLiu97/llmICL"],"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/olmo-accelerating-the-science-of-language","slug":"olmo-accelerating-the-science-of-language","title":"OLMo: Accelerating the Science of Language Models","date":"2024-02-01","arxiv_id":"2402.00838","repositories_listed":3,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/olmo-accelerating-the-science-of-language#ran","syntology_url":"https://syntology.ai/paper/2402.00838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00838"}},"official":{"repos":["allenai/olmo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/towards-efficient-and-exact-optimization-of","slug":"towards-efficient-and-exact-optimization-of","title":"Towards Efficient Exact Optimization of Language Model Alignment","date":"2024-02-01","arxiv_id":"2402.00856","repositories_listed":2,"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/towards-efficient-and-exact-optimization-of#ran","syntology_url":"https://syntology.ai/paper/2402.00856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00856"}},"official":{"repos":["haozheji/exact-optimization"],"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/when-benchmarks-are-targets-revealing-the","slug":"when-benchmarks-are-targets-revealing-the","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","date":"2024-02-01","arxiv_id":"2402.01781","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-benchmarks-are-targets-revealing-the#ran","syntology_url":"https://syntology.ai/paper/2402.01781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01781"}},"official":{"repos":["national-center-for-ai-saudi-arabia/lm-evaluation-harness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lanegraph2seq-lane-topology-extraction-with","slug":"lanegraph2seq-lane-topology-extraction-with","title":"LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement","date":"2024-01-31","arxiv_id":"2401.17609","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lanegraph2seq-lane-topology-extraction-with#ran","syntology_url":"https://syntology.ai/paper/2401.17609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17609"}},"official":{"repos":["fudan-zvg/roadnet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dolma-an-open-corpus-of-three-trillion-tokens","slug":"dolma-an-open-corpus-of-three-trillion-tokens","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","date":"2024-01-31","arxiv_id":"2402.00159","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/dolma-an-open-corpus-of-three-trillion-tokens#ran","syntology_url":"https://syntology.ai/paper/2402.00159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00159"}},"official":{"repos":["allenai/dolma"],"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/llamp-large-language-model-made-powerful-for","slug":"llamp-large-language-model-made-powerful-for","title":"LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation","date":"2024-01-30","arxiv_id":"2401.17244","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llamp-large-language-model-made-powerful-for#ran","syntology_url":"https://syntology.ai/paper/2401.17244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17244"}},"official":{"repos":["chiang-yuan/llamp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/yolo-world-real-time-open-vocabulary-object","slug":"yolo-world-real-time-open-vocabulary-object","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","date":"2024-01-30","arxiv_id":"2401.17270","repositories_listed":3,"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/yolo-world-real-time-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2401.17270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17270"}},"official":{"repos":["ailab-cvc/yolo-world"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/overcoming-the-pitfalls-of-vision-language","slug":"overcoming-the-pitfalls-of-vision-language","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization","date":"2024-01-29","arxiv_id":"2401.15914","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/overcoming-the-pitfalls-of-vision-language#ran","syntology_url":"https://syntology.ai/paper/2401.15914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15914"}},"official":{"repos":["apple/ml-ogen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/contextualization-distillation-from-large","slug":"contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","arxiv_id":"2402.01729","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contextualization-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2402.01729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01729"}},"official":{"repos":["david-li0406/contextulization-distillation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/l-autoda-leveraging-large-language-models-for","slug":"l-autoda-leveraging-large-language-models-for","title":"L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks","date":"2024-01-27","arxiv_id":"2401.15335","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l-autoda-leveraging-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.15335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15335"}},"official":{"repos":["pgg3/L-AutoDA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"e4f2413272ae00c31bfa9ba100ca58f9c966a4f23d74aeb4af9235eeb9d6d1f9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}