{"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":"/method/gpt-4/papers/ran/5","list_of":"/method/gpt-4","method":"GPT-4","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":5,"pages_in_order":6,"rows_per_page":100,"rows":[401,500],"of":526,"counts":{"archive_papers_tagged":2870,"with_a_code_link":1244,"where_syntology_ran_a_sample":526,"not_listed_spam_title":0,"listed":2870,"listed_where_code_ran":526,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":417,"every_run_a_failure_of_syntologys_instrument":109,"listed_with_a_run_with_no_instrument_failure":417,"listed_every_run_a_failure_of_syntologys_instrument":109,"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":"/method/gpt-4/papers/ran/1","prev":"/method/gpt-4/papers/ran/4","next":"/method/gpt-4/papers/ran/6","papers":[{"paper":"/paper/suspicion-agent-playing-imperfect-information","slug":"suspicion-agent-playing-imperfect-information","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","date":"2023-09-29","arxiv_id":"2309.17277","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cr-gjx/suspicion-agent"],"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"]}}},{"paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":9,"n_instrument":2,"unverified":1,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/lawbench-benchmarking-legal-knowledge-of","slug":"lawbench-benchmarking-legal-knowledge-of","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","date":"2023-09-28","arxiv_id":"2309.16289","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["open-compass/lawbench"],"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"]}}},{"paper":"/paper/gpt-fathom-benchmarking-large-language-models","slug":"gpt-fathom-benchmarking-large-language-models","title":"GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond","date":"2023-09-28","arxiv_id":"2309.16583","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["gpt-fathom/gpt-fathom"],"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"]}}},{"paper":"/paper/reconcile-round-table-conference-improves","slug":"reconcile-round-table-conference-improves","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","date":"2023-09-22","arxiv_id":"2309.13007","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["dinobby/reconcile"],"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"]}}},{"paper":"/paper/code-soliloquies-for-accurate-calculations-in","slug":"code-soliloquies-for-accurate-calculations-in","title":"Code Soliloquies for Accurate Calculations in Large Language Models","date":"2023-09-21","arxiv_id":"2309.12161","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["luffycodes/tutorbot-spock-phys"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-reversal-curse-llms-trained-on-a-is-b","slug":"the-reversal-curse-llms-trained-on-a-is-b","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","date":"2023-09-21","arxiv_id":"2309.12288","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lukasberglund/reversal_curse"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-self-reinforcement-for-improving","slug":"exploring-self-reinforcement-for-improving","title":"Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models","date":"2023-09-19","arxiv_id":"2309.10444","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["strong-ai-lab/explanation-generation"],"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"]}}},{"paper":"/paper/investlm-a-large-language-model-for","slug":"investlm-a-large-language-model-for","title":"InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning","date":"2023-09-15","arxiv_id":"2309.13064","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["abacinlp/investlm"],"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"]}}},{"paper":"/paper/safetybench-evaluating-the-safety-of-large","slug":"safetybench-evaluating-the-safety-of-large","title":"SafetyBench: Evaluating the Safety of Large Language Models","date":"2023-09-13","arxiv_id":"2309.07045","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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","official":{"repos":["thu-coai/safetybench"],"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"]}}},{"paper":"/paper/rain-your-language-models-can-align","slug":"rain-your-language-models-can-align","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","date":"2023-09-13","arxiv_id":"2309.07124","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SafeAILab/RAIN"],"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"]}}},{"paper":"/paper/large-language-models-for-automated-open","slug":"large-language-models-for-automated-open","title":"Large Language Models for Automated Open-domain Scientific Hypotheses Discovery","date":"2023-09-06","arxiv_id":"2309.02726","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"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) · 5 unverified","official":{"repos":["zongliny/moose"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-can-solve-mathematical-problems-without-a","slug":"gpt-can-solve-mathematical-problems-without-a","title":"GPT Can Solve Mathematical Problems Without a Calculator","date":"2023-09-06","arxiv_id":"2309.03241","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["thudm/mathglm"],"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"]}}},{"paper":"/paper/publicly-shareable-clinical-large-language","slug":"publicly-shareable-clinical-large-language","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","date":"2023-09-01","arxiv_id":"2309.00237","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["starmpcc/asclepius"],"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"]}}},{"paper":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["gersteinlab/biocoder"],"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"]}}},{"paper":"/paper/exploring-large-language-models-for-knowledge","slug":"exploring-large-language-models-for-knowledge","title":"Exploring Large Language Models for Knowledge Graph Completion","date":"2023-08-26","arxiv_id":"2308.13916","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["yao8839836/kg-llm"],"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"]}}},{"paper":"/paper/scieval-a-multi-level-large-language-model","slug":"scieval-a-multi-level-large-language-model","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","date":"2023-08-25","arxiv_id":"2308.13149","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["opendfm/bai-scieval","opendfm/scieval"],"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"]}}},{"paper":"/paper/do-not-answer-a-dataset-for-evaluating","slug":"do-not-answer-a-dataset-for-evaluating","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","date":"2023-08-25","arxiv_id":"2308.13387","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["libr-ai/do-not-answer"],"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"]}}},{"paper":"/paper/mllm-dataengine-an-iterative-refinement","slug":"mllm-dataengine-an-iterative-refinement","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","date":"2023-08-25","arxiv_id":"2308.13566","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opendatalab/mllm-dataengine"],"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"]}}},{"paper":"/paper/vigc-visual-instruction-generation-and","slug":"vigc-visual-instruction-generation-and","title":"VIGC: Visual Instruction Generation and Correction","date":"2023-08-24","arxiv_id":"2308.12714","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":2,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["opendatalab/vigc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructiongpt-4-a-200-instruction-paradigm","slug":"instructiongpt-4-a-200-instruction-paradigm","title":"InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4","date":"2023-08-23","arxiv_id":"2308.12067","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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","official":{"repos":["waltonfuture/InstructionGPT-4"],"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"]}}},{"paper":"/paper/out-of-the-cage-how-stochastic-parrots-win-in","slug":"out-of-the-cage-how-stochastic-parrots-win-in","title":"Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments","date":"2023-08-23","arxiv_id":"2308.12086","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"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","official":{"repos":["stratosphereips/netsecgame"],"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"]}}},{"paper":"/paper/evaluating-large-language-models-on-graphs","slug":"evaluating-large-language-models-on-graphs","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","date":"2023-08-22","arxiv_id":"2308.11224","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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","official":{"repos":["ayame1006/llmtograph"],"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"]}}},{"paper":"/paper/on-the-adversarial-robustness-of-multi-modal","slug":"on-the-adversarial-robustness-of-multi-modal","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","date":"2023-08-21","arxiv_id":"2308.10741","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chs20/robustvlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lateval-an-interactive-llms-evaluation","slug":"lateval-an-interactive-llms-evaluation","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles","date":"2023-08-21","arxiv_id":"2308.10855","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":9,"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) · 6 unverified","official":{"repos":["thukelab/lateval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/guinea-pig-trials-utilizing-gpt-a-novel-smart","slug":"guinea-pig-trials-utilizing-gpt-a-novel-smart","title":"\"Guinea Pig Trials\" Utilizing GPT: A Novel Smart Agent-Based Modeling Approach for Studying Firm Competition and Collusion","date":"2023-08-21","arxiv_id":"2308.10974","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["roihn/sabm","wuzengqing001225/sabm_pricing_game"],"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"]}}},{"paper":"/paper/expel-llm-agents-are-experiential-learners","slug":"expel-llm-agents-are-experiential-learners","title":"ExpeL: LLM Agents Are Experiential Learners","date":"2023-08-20","arxiv_id":"2308.10144","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["LeapLabTHU/ExpeL"],"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"]}}},{"paper":"/paper/stablellava-enhanced-visual-instruction","slug":"stablellava-enhanced-visual-instruction","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","date":"2023-08-20","arxiv_id":"2308.10253","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["icoz69/stablellava"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-study-on-robustness-and-reliability-of","slug":"a-study-on-robustness-and-reliability-of","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","date":"2023-08-20","arxiv_id":"2308.10335","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["floridsleeves/robustapi"],"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"]}}},{"paper":"/paper/fineval-a-chinese-financial-domain-knowledge","slug":"fineval-a-chinese-financial-domain-knowledge","title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","date":"2023-08-19","arxiv_id":"2308.09975","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["sufe-aiflm-lab/fineval"],"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"]}}},{"paper":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":16,"phrase":"10 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; 2 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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","official":{"repos":["wyl-willing/MindMap"],"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"]}}},{"paper":"/paper/time-travel-in-llms-tracing-data","slug":"time-travel-in-llms-tracing-data","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","date":"2023-08-16","arxiv_id":"2308.08493","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["shahriargolchin/time-travel-in-llms"],"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"]}}},{"paper":"/paper/dialogue-for-prompting-a-policy-gradient","slug":"dialogue-for-prompting-a-policy-gradient","title":"Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning","date":"2023-08-14","arxiv_id":"2308.07272","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":1,"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","official":{"repos":["czx-li/DP2O"],"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"]}}},{"paper":"/paper/gpt-4-is-too-smart-to-be-safe-stealthy-chat","slug":"gpt-4-is-too-smart-to-be-safe-stealthy-chat","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","date":"2023-08-12","arxiv_id":"2308.06463","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["robustnlp/cipherchat"],"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"]}}},{"paper":"/paper/visit-bench-a-benchmark-for-vision-language","slug":"visit-bench-a-benchmark-for-vision-language","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","date":"2023-08-12","arxiv_id":"2308.06595","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":3,"n_instrument":6,"unverified":0,"pointer_only":9,"phrase":"9 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mlfoundations/VisIT-Bench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-deductive-reasoning-from-synthetic","slug":"learning-deductive-reasoning-from-synthetic","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","date":"2023-08-11","arxiv_id":"2308.07336","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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","official":{"repos":["hitachi-nlp/fld"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/scigraphqa-a-large-scale-synthetic-multi-turn","slug":"scigraphqa-a-large-scale-synthetic-multi-turn","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","date":"2023-08-07","arxiv_id":"2308.03349","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["findalexli/SciGraphQA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/emotionally-numb-or-empathetic-evaluating-how","slug":"emotionally-numb-or-empathetic-evaluating-how","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","date":"2023-08-07","arxiv_id":"2308.03656","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":10,"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) · 0 unverified","official":{"repos":["cuhk-arise/emotionbench"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-anything-now-characterizing-and-evaluating","slug":"do-anything-now-characterizing-and-evaluating","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","date":"2023-08-07","arxiv_id":"2308.03825","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["verazuo/jailbreak_llms"],"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"]}}},{"paper":"/paper/flows-building-blocks-of-reasoning-and","slug":"flows-building-blocks-of-reasoning-and","title":"Flows: Building Blocks of Reasoning and Collaborating AI","date":"2023-08-02","arxiv_id":"2308.01285","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["epfl-dlab/aiflows","epfl-dlab/cc_flows"],"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"]}}},{"paper":"/paper/chathome-development-and-evaluation-of-a","slug":"chathome-development-and-evaluation-of-a","title":"ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation","date":"2023-07-28","arxiv_id":"2307.15290","n_code_links":1,"syntology":{"ran":7,"of":17,"n_ran_checked":4,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"7 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; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["lianjiatech/belle"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-clip-with-gpt-4-harnessing-visual","slug":"enhancing-clip-with-gpt-4-harnessing-visual","title":"Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts","date":"2023-07-21","arxiv_id":"2307.11661","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":1,"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","official":{"repos":["mayug/vdt-adapter"],"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"]}}},{"paper":"/paper/l-eval-instituting-standardized-evaluation","slug":"l-eval-instituting-standardized-evaluation","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","date":"2023-07-20","arxiv_id":"2307.11088","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["openlmlab/leval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lchen001/llmdrift"],"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":["listed","official"]}}},{"paper":"/paper/collie-systematic-construction-of-constrained","slug":"collie-systematic-construction-of-constrained","title":"COLLIE: Systematic Construction of Constrained Text Generation Tasks","date":"2023-07-17","arxiv_id":"2307.08689","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["princeton-nlp/Collie"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/alpagasus-training-a-better-alpaca-with-fewer","slug":"alpagasus-training-a-better-alpaca-with-fewer","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","date":"2023-07-17","arxiv_id":"2307.08701","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gpt4life/alpagasus"],"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"]}}},{"paper":"/paper/think-on-graph-deep-and-responsible-reasoning","slug":"think-on-graph-deep-and-responsible-reasoning","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","date":"2023-07-15","arxiv_id":"2307.07697","n_code_links":3,"syntology":{"ran":12,"of":16,"n_ran_checked":10,"n_instrument":2,"unverified":4,"pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["gasolsun36/tog","idea-finai/tog"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/leveraging-large-language-models-to-generate","slug":"leveraging-large-language-models-to-generate","title":"Leveraging Large Language Models to Generate Answer Set Programs","date":"2023-07-15","arxiv_id":"2307.07699","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["azreasoners/gpt-asp-rules"],"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"]}}},{"paper":"/paper/teaching-arithmetic-to-small-transformers","slug":"teaching-arithmetic-to-small-transformers","title":"Teaching Arithmetic to Small Transformers","date":"2023-07-07","arxiv_id":"2307.03381","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["lee-ny/teaching_arithmetic"],"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"]}}},{"paper":"/paper/umass-bionlp-at-mediqa-chat-2023-can-llms","slug":"umass-bionlp-at-mediqa-chat-2023-can-llms","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","date":"2023-06-29","arxiv_id":"2306.16931","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["believewhat/dr.noteaid"],"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"]}}},{"paper":"/paper/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":2,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SALT-NLP/LLaVAR"],"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":["listed","official","unlocated"]}}},{"paper":"/paper/leandojo-theorem-proving-with-retrieval-1","slug":"leandojo-theorem-proving-with-retrieval-1","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","date":"2023-06-27","arxiv_id":"2306.15626","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":1,"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","official":{"repos":["lean-dojo/leandojo","lean-dojo/leandojochatgpt","lean-dojo/reprover"],"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"]}}},{"paper":"/paper/can-llms-express-their-uncertainty-an","slug":"can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","date":"2023-06-22","arxiv_id":"2306.13063","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["miaoxiong2320/llm-uncertainty"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-language-networks-joint-prompt-training","slug":"deep-language-networks-joint-prompt-training","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","date":"2023-06-21","arxiv_id":"2306.12509","n_code_links":1,"syntology":{"ran":3,"of":19,"n_ran_checked":0,"n_instrument":3,"unverified":16,"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) · 16 unverified","official":{"repos":["microsoft/deep-language-networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]}}},{"paper":"/paper/aries-a-corpus-of-scientific-paper-edits-made","slug":"aries-a-corpus-of-scientific-paper-edits-made","title":"ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews","date":"2023-06-21","arxiv_id":"2306.12587","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/aries"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1","slug":"judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","arxiv_id":"2306.05685","n_code_links":11,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lm-sys/fastchat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/14-examples-of-how-llms-can-transform","slug":"14-examples-of-how-llms-can-transform","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","date":"2023-06-09","arxiv_id":"2306.06283","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["qai222/llm_organic_synthesis","doncamilom/bollama"],"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"]}}},{"paper":"/paper/toolalpaca-generalized-tool-learning-for","slug":"toolalpaca-generalized-tool-learning-for","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","date":"2023-06-08","arxiv_id":"2306.05301","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["tangqiaoyu/ToolAlpaca"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-far-can-camels-go-exploring-the-state-of","slug":"how-far-can-camels-go-exploring-the-state-of","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","date":"2023-06-07","arxiv_id":"2306.04751","n_code_links":4,"syntology":{"ran":6,"of":12,"n_ran_checked":2,"n_instrument":4,"unverified":6,"pointer_only":2,"phrase":"6 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; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["allenai/open-instruct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/instructeval-towards-holistic-evaluation-of","slug":"instructeval-towards-holistic-evaluation-of","title":"INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models","date":"2023-06-07","arxiv_id":"2306.04757","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["declare-lab/instruct-eval"],"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"]}}},{"paper":"/paper/benchmarking-large-language-models-on-cmexam","slug":"benchmarking-large-language-models-on-cmexam","title":"Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset","date":"2023-06-05","arxiv_id":"2306.03030","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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","official":{"repos":["williamliujl/cmexam"],"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"]}}},{"paper":"/paper/auto-gpt-for-online-decision-making","slug":"auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","arxiv_id":"2306.02224","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":4,"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) · 5 unverified","official":{"repos":["younghuman/llmagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-verification-improves-few-shot-clinical","slug":"self-verification-improves-few-shot-clinical","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","date":"2023-05-30","arxiv_id":"2306.00024","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["microsoft/clinical-self-verification"],"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"]}}},{"paper":"/paper/the-rise-of-ai-language-pathologists","slug":"the-rise-of-ai-language-pathologists","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","date":"2023-05-29","arxiv_id":"2305.17891","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["miccaiif/top"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-are-not-fair-evaluators","slug":"large-language-models-are-not-fair-evaluators","title":"Large Language Models are not Fair Evaluators","date":"2023-05-29","arxiv_id":"2305.17926","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["i-eval/faireval"],"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"]}}},{"paper":"/paper/marked-personas-using-natural-language","slug":"marked-personas-using-natural-language","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","date":"2023-05-29","arxiv_id":"2305.18189","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["myracheng/markedpersonas"],"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"]}}},{"paper":"/paper/do-language-models-know-when-they-re","slug":"do-language-models-know-when-they-re","title":"Do Language Models Know When They're Hallucinating References?","date":"2023-05-29","arxiv_id":"2305.18248","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/hallucinated-references"],"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"]}}},{"paper":"/paper/dna-gpt-divergent-n-gram-analysis-for","slug":"dna-gpt-divergent-n-gram-analysis-for","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","date":"2023-05-27","arxiv_id":"2305.17359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["xianjun-yang/dna-gpt"],"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"]}}},{"paper":"/paper/swiftsage-a-generative-agent-with-fast-and-1","slug":"swiftsage-a-generative-agent-with-fast-and-1","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","date":"2023-05-27","arxiv_id":"2305.17390","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/on-evaluating-adversarial-robustness-of-large","slug":"on-evaluating-adversarial-robustness-of-large","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","date":"2023-05-26","arxiv_id":"2305.16934","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yunqing-me/attackvlm"],"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"]}}},{"paper":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gengzezhou/navgpt"],"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":["listed","official"]}}},{"paper":"/paper/biomedgpt-a-unified-and-generalist-biomedical","slug":"biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","arxiv_id":"2305.17100","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":7,"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) · 2 unverified","official":{"repos":["taokz/biomedgpt"],"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"]}}},{"paper":"/paper/chain-of-thought-hub-a-continuous-effort-to","slug":"chain-of-thought-hub-a-continuous-effort-to","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","date":"2023-05-26","arxiv_id":"2305.17306","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["franxyao/chain-of-thought-hub"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-contradictory-hallucinations-of-large","slug":"self-contradictory-hallucinations-of-large","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","date":"2023-05-25","arxiv_id":"2305.15852","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["eth-sri/chatprotect"],"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"]}}},{"paper":"/paper/voyager-an-open-ended-embodied-agent-with","slug":"voyager-an-open-ended-embodied-agent-with","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","date":"2023-05-25","arxiv_id":"2305.16291","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["MineDojo/Voyager"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/landmark-attention-random-access-infinite","slug":"landmark-attention-random-access-infinite","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","date":"2023-05-25","arxiv_id":"2305.16300","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":5,"n_instrument":6,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["epfml/landmark-attention"],"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":["community","listed","official"]}}},{"paper":"/paper/on-the-tool-manipulation-capability-of-open","slug":"on-the-tool-manipulation-capability-of-open","title":"On the Tool Manipulation Capability of Open-source Large Language Models","date":"2023-05-25","arxiv_id":"2305.16504","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sambanova/toolbench"],"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"]}}},{"paper":"/paper/from-words-to-wires-generating-functioning","slug":"from-words-to-wires-generating-functioning","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","date":"2023-05-24","arxiv_id":"2305.14874","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["cognitiveailab/words2wires"],"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"]}}},{"paper":"/paper/bytesized32-a-corpus-and-challenge-task-for","slug":"bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","date":"2023-05-24","arxiv_id":"2305.14879","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["cognitiveailab/bytesized32"],"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"]}}},{"paper":"/paper/towards-reliable-misinformation-mitigation","slug":"towards-reliable-misinformation-mitigation","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","date":"2023-05-24","arxiv_id":"2305.14928","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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","official":{"repos":["complexdata-mila/mitigatemisinfo"],"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"]}}},{"paper":"/paper/reasoning-with-language-model-is-planning","slug":"reasoning-with-language-model-is-planning","title":"Reasoning with Language Model is Planning with World Model","date":"2023-05-24","arxiv_id":"2305.14992","n_code_links":3,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["owaski/autoplan"],"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"]}}},{"paper":"/paper/have-llms-advanced-enough-a-challenging","slug":"have-llms-advanced-enough-a-challenging","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","date":"2023-05-24","arxiv_id":"2305.15074","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["hgaurav2k/jeebench"],"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":["found_in_text"]}}},{"paper":"/paper/huatuogpt-towards-taming-language-model-to-be","slug":"huatuogpt-towards-taming-language-model-to-be","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","date":"2023-05-24","arxiv_id":"2305.15075","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["freedomintelligence/huatuogpt"],"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"]}}},{"paper":"/paper/peek-across-improving-multi-document-modeling","slug":"peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","date":"2023-05-24","arxiv_id":"2305.15387","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":11,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"12 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; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["aviclu/peekacross"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/harnessing-the-power-of-large-language-models","slug":"harnessing-the-power-of-large-language-models","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","date":"2023-05-24","arxiv_id":"2305.15541","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["gblackout/logicllama"],"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"]}}},{"paper":"/paper/aligning-large-language-models-through","slug":"aligning-large-language-models-through","title":"Aligning Large Language Models through Synthetic Feedback","date":"2023-05-23","arxiv_id":"2305.13735","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["naver-ai/almost"],"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"]}}},{"paper":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long","slug":"zeroscrolls-a-zero-shot-benchmark-for-long","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","date":"2023-05-23","arxiv_id":"2305.14196","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["tau-nlp/zero_scrolls"],"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"]}}},{"paper":"/paper/factscore-fine-grained-atomic-evaluation-of","slug":"factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","arxiv_id":"2305.14251","n_code_links":4,"syntology":{"ran":11,"of":15,"n_ran_checked":10,"n_instrument":1,"unverified":4,"pointer_only":6,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shmsw25/factscore"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["stanford-oval/wikichat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","n_code_links":20,"syntology":{"ran":18,"of":26,"n_ran_checked":6,"n_instrument":12,"unverified":8,"pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"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":["community","listed","official","unlocated"]}}},{"paper":"/paper/dynosaur-a-dynamic-growth-paradigm-for","slug":"dynosaur-a-dynamic-growth-paradigm-for","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","date":"2023-05-23","arxiv_id":"2305.14327","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["wadeyin9712/dynosaur"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["xuzhao0/model-selection-reasoning"],"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"]}}},{"paper":"/paper/are-large-language-models-good-evaluators-for","slug":"are-large-language-models-good-evaluators-for","title":"Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization","date":"2023-05-22","arxiv_id":"2305.13091","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["damo-nlp-sg/llm_summeval"],"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"]}}},{"paper":"/paper/evaluating-the-performance-of-large-language","slug":"evaluating-the-performance-of-large-language","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","date":"2023-05-21","arxiv_id":"2305.12474","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["openlmlab/gaokao-bench"],"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"]}}},{"paper":"/paper/theoremqa-a-theorem-driven-question-answering","slug":"theoremqa-a-theorem-driven-question-answering","title":"TheoremQA: A Theorem-driven Question Answering dataset","date":"2023-05-21","arxiv_id":"2305.12524","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":8,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"10 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wenhuchen/theoremqa"],"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":["found_in_text","official"]}}},{"paper":"/paper/diving-into-the-inter-consistency-of-large","slug":"diving-into-the-inter-consistency-of-large","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","date":"2023-05-19","arxiv_id":"2305.11595","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["waste-wood/ford"],"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"]}}},{"paper":"/paper/generalized-planning-in-pddl-domains-with","slug":"generalized-planning-in-pddl-domains-with","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","date":"2023-05-18","arxiv_id":"2305.11014","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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","official":{"repos":["tomsilver/llm-genplan"],"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"]}}},{"paper":"/paper/tree-of-thoughts-deliberate-problem-solving-1","slug":"tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","n_code_links":6,"syntology":{"ran":19,"of":24,"n_ran_checked":18,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"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":["community","listed","official"]}}}],"record_sha256":"eac57cc5c298cdad889364ee23038eb65da5c1178f5983fb6e67a225b832c52b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}