{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/large-language-model/papers/ran/8","list_of":"/task/large-language-model","task":"Large Language Model","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"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":8,"pages_in_order":9,"rows_per_page":100,"rows":[701,800],"of":801,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/large-language-model/papers/ran/1","prev":"/task/large-language-model/papers/ran/7","next":"/task/large-language-model/papers/ran/9","papers":[{"url":"/paper/epidemic-modeling-with-generative-agents","slug":"epidemic-modeling-with-generative-agents","title":"Epidemic Modeling with Generative Agents","date":"2023-07-11","arxiv_id":"2307.04986","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/epidemic-modeling-with-generative-agents#ran","syntology_url":"https://syntology.ai/paper/2307.04986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04986"}},"official":{"repos":["bear96/gabm-epidemic"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-large-language-model-for-graph-data","slug":"exploring-large-language-model-for-graph-data","title":"Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations","date":"2023-07-10","arxiv_id":"2307.05722","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/exploring-large-language-model-for-graph-data#ran","syntology_url":"https://syntology.ai/paper/2307.05722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05722"}},"official":{"repos":["wlik/glrec"],"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/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","repositories_listed":3,"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":5,"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/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}},"official":{"repos":["jshilong/gpt4roi"],"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/prd-peer-rank-and-discussion-improve-large","slug":"prd-peer-rank-and-discussion-improve-large","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","date":"2023-07-06","arxiv_id":"2307.02762","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prd-peer-rank-and-discussion-improve-large#ran","syntology_url":"https://syntology.ai/paper/2307.02762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02762"}},"official":{"repos":["bcdnlp/prd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/flacuna-unleashing-the-problem-solving-power","slug":"flacuna-unleashing-the-problem-solving-power","title":"Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning","date":"2023-07-05","arxiv_id":"2307.02053","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flacuna-unleashing-the-problem-solving-power#ran","syntology_url":"https://syntology.ai/paper/2307.02053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02053"}},"official":{"repos":["declare-lab/flacuna"],"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/causal-discovery-with-language-models-as","slug":"causal-discovery-with-language-models-as","title":"Causal Discovery with Language Models as Imperfect Experts","date":"2023-07-05","arxiv_id":"2307.02390","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":5,"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/causal-discovery-with-language-models-as#ran","syntology_url":"https://syntology.ai/paper/2307.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02390"}},"official":{"repos":["stephlong614/causal-disco"],"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/text-based-large-language-model-for","slug":"text-based-large-language-model-for","title":"GenRec: Large Language Model for Generative Recommendation","date":"2023-07-02","arxiv_id":"2307.00457","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/text-based-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2307.00457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00457"}},"official":{"repos":["rutgerswiselab/genrec"],"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/large-language-models-enable-few-shot","slug":"large-language-models-enable-few-shot","title":"Large Language Models Enable Few-Shot Clustering","date":"2023-07-02","arxiv_id":"2307.00524","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-enable-few-shot#ran","syntology_url":"https://syntology.ai/paper/2307.00524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00524"}},"official":{"repos":["viswavi/few-shot-clustering"],"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/large-language-model-as-attributed-training-1","slug":"large-language-model-as-attributed-training-1","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","date":"2023-06-28","arxiv_id":"2306.15895","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"12 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; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/large-language-model-as-attributed-training-1#ran","syntology_url":"https://syntology.ai/paper/2306.15895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15895"}},"official":{"repos":["yueyu1030/attrprompt"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/palm-predicting-actions-through-language","slug":"palm-predicting-actions-through-language","title":"Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023","date":"2023-06-28","arxiv_id":"2306.16545","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":1,"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/palm-predicting-actions-through-language#ran","syntology_url":"https://syntology.ai/paper/2306.16545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16545"}},"official":{"repos":["dandoge/palm"],"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/reflect-summarizing-robot-experiences-for","slug":"reflect-summarizing-robot-experiences-for","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","date":"2023-06-27","arxiv_id":"2306.15724","repositories_listed":1,"syntology":{"n":19,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/reflect-summarizing-robot-experiences-for#ran","syntology_url":"https://syntology.ai/paper/2306.15724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15724"}},"official":{"repos":["real-stanford/reflect"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/hyenadna-long-range-genomic-sequence-modeling","slug":"hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","arxiv_id":"2306.15794","repositories_listed":4,"syntology":{"n":28,"n_ran":17,"n_constructed":11,"n_ran_checked":13,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":1,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/hyenadna-long-range-genomic-sequence-modeling#ran","syntology_url":"https://syntology.ai/paper/2306.15794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15794"}},"official":{"repos":["HazyResearch/hyena-dna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/composing-parameter-efficient-modules-with","slug":"composing-parameter-efficient-modules-with","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","date":"2023-06-26","arxiv_id":"2306.14870","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/composing-parameter-efficient-modules-with#ran","syntology_url":"https://syntology.ai/paper/2306.14870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14870"}},"official":{"repos":["hkust-nlp/pem_composition","sjtu-lit/pem_composition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/desco-learning-object-recognition-with-rich","slug":"desco-learning-object-recognition-with-rich","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","date":"2023-06-24","arxiv_id":"2306.14060","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/desco-learning-object-recognition-with-rich#ran","syntology_url":"https://syntology.ai/paper/2306.14060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.14060"}},"official":null}},{"url":"/paper/cmmlu-measuring-massive-multitask-language","slug":"cmmlu-measuring-massive-multitask-language","title":"CMMLU: Measuring massive multitask language understanding in Chinese","date":"2023-06-15","arxiv_id":"2306.09212","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":2,"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/cmmlu-measuring-massive-multitask-language#ran","syntology_url":"https://syntology.ai/paper/2306.09212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09212"}},"official":{"repos":["haonan-li/cmmlu"],"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/int2-1-towards-fine-tunable-quantized-large","slug":"int2-1-towards-fine-tunable-quantized-large","title":"INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation","date":"2023-06-13","arxiv_id":"2306.08162","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/int2-1-towards-fine-tunable-quantized-large#ran","syntology_url":"https://syntology.ai/paper/2306.08162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08162"}},"official":{"repos":["stochasticai/xturing"],"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/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","repositories_listed":11,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.05685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05685"}},"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"]}}},{"url":"/paper/fingpt-open-source-financial-large-language","slug":"fingpt-open-source-financial-large-language","title":"FinGPT: Open-Source Financial Large Language Models","date":"2023-06-09","arxiv_id":"2306.06031","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/fingpt-open-source-financial-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.06031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06031"}},"official":{"repos":["ai4finance-foundation/fingpt","ai4finance-foundation/finnlp"],"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"]}}},{"url":"/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","repositories_listed":2,"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":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","sample_list":"/paper/14-examples-of-how-llms-can-transform#ran","syntology_url":"https://syntology.ai/paper/2306.06283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06283"}},"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"]}}},{"url":"/paper/large-language-models-are-semi-parametric-1","slug":"large-language-models-are-semi-parametric-1","title":"Large Language Models Are Semi-Parametric Reinforcement Learning Agents","date":"2023-06-09","arxiv_id":"2306.07929","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/large-language-models-are-semi-parametric-1#ran","syntology_url":"https://syntology.ai/paper/2306.07929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07929"}},"official":{"repos":["opendfm/rememberer"],"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/pandalm-an-automatic-evaluation-benchmark-for","slug":"pandalm-an-automatic-evaluation-benchmark-for","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","date":"2023-06-08","arxiv_id":"2306.05087","repositories_listed":2,"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":0,"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/pandalm-an-automatic-evaluation-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2306.05087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05087"}},"official":{"repos":["weopenml/pandalm"],"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":["listed","official"]}}},{"url":"/paper/reta-llm-a-retrieval-augmented-large-language","slug":"reta-llm-a-retrieval-augmented-large-language","title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","date":"2023-06-08","arxiv_id":"2306.05212","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/reta-llm-a-retrieval-augmented-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.05212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05212"}},"official":{"repos":["ruc-gsai/yulan-ir"],"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/pixiu-a-large-language-model-instruction-data","slug":"pixiu-a-large-language-model-instruction-data","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","date":"2023-06-08","arxiv_id":"2306.05443","repositories_listed":2,"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/pixiu-a-large-language-model-instruction-data#ran","syntology_url":"https://syntology.ai/paper/2306.05443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05443"}},"official":{"repos":["chancefocus/pixiu"],"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/youku-mplug-a-10-million-large-scale-chinese","slug":"youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","arxiv_id":"2306.04362","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/youku-mplug-a-10-million-large-scale-chinese#ran","syntology_url":"https://syntology.ai/paper/2306.04362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04362"}},"official":{"repos":["x-plug/youku-mplug"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/spqr-a-sparse-quantized-representation-for","slug":"spqr-a-sparse-quantized-representation-for","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","date":"2023-06-05","arxiv_id":"2306.03078","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":1,"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/spqr-a-sparse-quantized-representation-for#ran","syntology_url":"https://syntology.ai/paper/2306.03078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03078"}},"official":{"repos":["vahe1994/spqr"],"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","unlocated"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_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","sample_list":"/paper/the-rise-of-ai-language-pathologists#ran","syntology_url":"https://syntology.ai/paper/2305.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17891"}},"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"]}}},{"url":"/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","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/large-language-models-are-not-fair-evaluators#ran","syntology_url":"https://syntology.ai/paper/2305.17926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17926"}},"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"]}}},{"url":"/paper/instructedit-improving-automatic-masks-for","slug":"instructedit-improving-automatic-masks-for","title":"InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions","date":"2023-05-29","arxiv_id":"2305.18047","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/instructedit-improving-automatic-masks-for#ran","syntology_url":"https://syntology.ai/paper/2305.18047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18047"}},"official":{"repos":["qianwangx/instructedit"],"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/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":29,"n_instrument":6,"n_unverified":7,"n_honours":2,"n_violates":1,"n_no_contract":26,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 1 violated, 26 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/language-models-can-improve-event-prediction-1","slug":"language-models-can-improve-event-prediction-1","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","date":"2023-05-26","arxiv_id":"2305.16646","repositories_listed":2,"syntology":{"n":24,"n_ran":19,"n_constructed":4,"n_ran_checked":17,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":16,"n_pointer_only":4,"phrase":"19 ran (of which 4 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 1 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/language-models-can-improve-event-prediction-1#ran","syntology_url":"https://syntology.ai/paper/2305.16646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16646"}},"official":{"repos":["ant-research/easytemporalpointprocess","ilampard/lamp"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/generatect-text-guided-3d-chest-ct-generation","slug":"generatect-text-guided-3d-chest-ct-generation","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","date":"2023-05-25","arxiv_id":"2305.16037","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":4,"n_no_contract":8,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 4 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generatect-text-guided-3d-chest-ct-generation#ran","syntology_url":"https://syntology.ai/paper/2305.16037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16037"}},"official":{"repos":["ibrahimethemhamamci/generatect"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chatbridge-bridging-modalities-with-large","slug":"chatbridge-bridging-modalities-with-large","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","date":"2023-05-25","arxiv_id":"2305.16103","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chatbridge-bridging-modalities-with-large#ran","syntology_url":"https://syntology.ai/paper/2305.16103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16103"}},"official":null}},{"url":"/paper/expertprompting-instructing-large-language","slug":"expertprompting-instructing-large-language","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","date":"2023-05-24","arxiv_id":"2305.14688","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":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/expertprompting-instructing-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14688"}},"official":{"repos":["ofa-sys/expertllama"],"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/beamsearchqa-large-language-models-are-strong","slug":"beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","arxiv_id":"2305.14766","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/beamsearchqa-large-language-models-are-strong#ran","syntology_url":"https://syntology.ai/paper/2305.14766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14766"}},"official":{"repos":["microsoft/simxns"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/clusterllm-large-language-models-as-a-guide","slug":"clusterllm-large-language-models-as-a-guide","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","date":"2023-05-24","arxiv_id":"2305.14871","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clusterllm-large-language-models-as-a-guide#ran","syntology_url":"https://syntology.ai/paper/2305.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14871"}},"official":{"repos":["zhang-yu-wei/clusterllm"],"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/pivoine-instruction-tuning-for-open-world","slug":"pivoine-instruction-tuning-for-open-world","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","date":"2023-05-24","arxiv_id":"2305.14898","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":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) · 2 unverified","sample_list":"/paper/pivoine-instruction-tuning-for-open-world#ran","syntology_url":"https://syntology.ai/paper/2305.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14898"}},"official":{"repos":["lukeming-tsinghua/instruction-tuning-for-open-world-ie"],"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/how-predictable-are-large-language-model","slug":"how-predictable-are-large-language-model","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","date":"2023-05-24","arxiv_id":"2305.14947","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/how-predictable-are-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14947"}},"official":{"repos":["ink-usc/predicting-big-bench"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/llmdet-a-large-language-models-detection-tool#ran","syntology_url":"https://syntology.ai/paper/2305.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15004"}},"official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/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","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/prompt-optimization-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15064"}},"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"]}}},{"url":"/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","repositories_listed":2,"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/huatuogpt-towards-taming-language-model-to-be#ran","syntology_url":"https://syntology.ai/paper/2305.15075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15075"}},"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"]}}},{"url":"/paper/think-before-you-act-decision-transformers","slug":"think-before-you-act-decision-transformers","title":"Think Before You Act: Decision Transformers with Working Memory","date":"2023-05-24","arxiv_id":"2305.16338","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/think-before-you-act-decision-transformers#ran","syntology_url":"https://syntology.ai/paper/2305.16338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16338"}},"official":{"repos":["luciferkonn/dt_mem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-from-mistakes-through-cooperative","slug":"learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13829","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"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, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learn-from-mistakes-through-cooperative#ran","syntology_url":"https://syntology.ai/paper/2305.13829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13829"}},"official":{"repos":["dqwang122/salam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/preserving-knowledge-invariance-rethinking","slug":"preserving-knowledge-invariance-rethinking","title":"Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction","date":"2023-05-23","arxiv_id":"2305.13981","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/preserving-knowledge-invariance-rethinking#ran","syntology_url":"https://syntology.ai/paper/2305.13981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13981"}},"official":{"repos":["qijimrc/robust"],"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/hierarchical-prompting-assists-large-language","slug":"hierarchical-prompting-assists-large-language","title":"Hierarchical Prompting Assists Large Language Model on Web Navigation","date":"2023-05-23","arxiv_id":"2305.14257","repositories_listed":3,"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":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","sample_list":"/paper/hierarchical-prompting-assists-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14257"}},"official":{"repos":["robert1003/ash-prompting"],"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/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","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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","sample_list":"/paper/wikichat-a-few-shot-llm-based-chatbot#ran","syntology_url":"https://syntology.ai/paper/2305.14292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14292"}},"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"]}}},{"url":"/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","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/automatic-model-selection-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14333"}},"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"]}}},{"url":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathdial-a-dialogue-tutoring-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2305.14536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14536"}},"official":{"repos":["eth-nlped/mathdial"],"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/2305-14585","slug":"2305-14585","title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models","date":"2023-05-23","arxiv_id":"2305.14585","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2305-14585#ran","syntology_url":"https://syntology.ai/paper/2305.14585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14585"}},"official":{"repos":["pnnl/projection_ntk"],"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/lion-adversarial-distillation-of-closed","slug":"lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","arxiv_id":"2305.12870","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"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; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lion-adversarial-distillation-of-closed#ran","syntology_url":"https://syntology.ai/paper/2305.12870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12870"}},"official":{"repos":["yjiangcm/lion"],"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"]}}},{"url":"/paper/making-language-models-better-tool-learners","slug":"making-language-models-better-tool-learners","title":"Making Language Models Better Tool Learners with Execution Feedback","date":"2023-05-22","arxiv_id":"2305.13068","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/making-language-models-better-tool-learners#ran","syntology_url":"https://syntology.ai/paper/2305.13068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13068"}},"official":{"repos":["zjunlp/trice"],"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/chain-of-knowledge-a-framework-for-grounding","slug":"chain-of-knowledge-a-framework-for-grounding","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","date":"2023-05-22","arxiv_id":"2305.13269","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":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chain-of-knowledge-a-framework-for-grounding#ran","syntology_url":"https://syntology.ai/paper/2305.13269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13269"}},"official":{"repos":["damo-nlp-sg/chain-of-knowledge"],"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/recurrentgpt-interactive-generation-of","slug":"recurrentgpt-interactive-generation-of","title":"RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text","date":"2023-05-22","arxiv_id":"2305.13304","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/recurrentgpt-interactive-generation-of#ran","syntology_url":"https://syntology.ai/paper/2305.13304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13304"}},"official":{"repos":["aiwaves-cn/recurrentgpt"],"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"]}}},{"url":"/paper/clinical-camel-an-open-source-expert-level","slug":"clinical-camel-an-open-source-expert-level","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","date":"2023-05-19","arxiv_id":"2305.12031","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clinical-camel-an-open-source-expert-level#ran","syntology_url":"https://syntology.ai/paper/2305.12031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12031"}},"official":{"repos":["bowang-lab/clinical-camel"],"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/speechgpt-empowering-large-language-models","slug":"speechgpt-empowering-large-language-models","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","date":"2023-05-18","arxiv_id":"2305.11000","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/speechgpt-empowering-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2305.11000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11000"}},"official":{"repos":["0nutation/speechgpt"],"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/visionllm-large-language-model-is-also-an","slug":"visionllm-large-language-model-is-also-an","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","date":"2023-05-18","arxiv_id":"2305.11175","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"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: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visionllm-large-language-model-is-also-an#ran","syntology_url":"https://syntology.ai/paper/2305.11175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11175"}},"official":{"repos":["opengvlab/visionllm","opengvlab/interngpt"],"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/pmc-vqa-visual-instruction-tuning-for-medical","slug":"pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10415","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pmc-vqa-visual-instruction-tuning-for-medical#ran","syntology_url":"https://syntology.ai/paper/2305.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10415"}},"official":{"repos":["xiaoman-zhang/PMC-VQA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/structgpt-a-general-framework-for-large","slug":"structgpt-a-general-framework-for-large","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","date":"2023-05-16","arxiv_id":"2305.09645","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":2,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":3,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 3 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/structgpt-a-general-framework-for-large#ran","syntology_url":"https://syntology.ai/paper/2305.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09645"}},"official":{"repos":["rucaibox/structgpt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-guided-tree-of-thought","slug":"large-language-model-guided-tree-of-thought","title":"Large Language Model Guided Tree-of-Thought","date":"2023-05-15","arxiv_id":"2305.08291","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/large-language-model-guided-tree-of-thought#ran","syntology_url":"https://syntology.ai/paper/2305.08291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08291"}},"official":{"repos":["jieyilong/tree-of-thought-puzzle-solver"],"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/investigating-emergent-goal-like-behaviour-in","slug":"investigating-emergent-goal-like-behaviour-in","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","date":"2023-05-13","arxiv_id":"2305.07970","repositories_listed":2,"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/investigating-emergent-goal-like-behaviour-in#ran","syntology_url":"https://syntology.ai/paper/2305.07970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07970"}},"official":{"repos":["phelps-sg/llm-cooperation","gitlab.com/sphelps/llm-cooperation"],"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/automatic-evaluation-of-attribution-by-large","slug":"automatic-evaluation-of-attribution-by-large","title":"Automatic Evaluation of Attribution by Large Language Models","date":"2023-05-10","arxiv_id":"2305.06311","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":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","sample_list":"/paper/automatic-evaluation-of-attribution-by-large#ran","syntology_url":"https://syntology.ai/paper/2305.06311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06311"}},"official":{"repos":["osu-nlp-group/attrscore"],"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/deeptextmark-deep-learning-based-text","slug":"deeptextmark-deep-learning-based-text","title":"DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large Language Model Generated Text","date":"2023-05-09","arxiv_id":"2305.05773","repositories_listed":4,"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":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","sample_list":"/paper/deeptextmark-deep-learning-based-text#ran","syntology_url":"https://syntology.ai/paper/2305.05773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05773"}},"official":null}},{"url":"/paper/x-llm-bootstrapping-advanced-large-language","slug":"x-llm-bootstrapping-advanced-large-language","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","date":"2023-05-07","arxiv_id":"2305.04160","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/x-llm-bootstrapping-advanced-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.04160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04160"}},"official":null}},{"url":"/paper/2x-faster-language-model-pre-training-via","slug":"2x-faster-language-model-pre-training-via","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","date":"2023-05-04","arxiv_id":"2305.02869","repositories_listed":1,"syntology":{"n":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/2x-faster-language-model-pre-training-via#ran","syntology_url":"https://syntology.ai/paper/2305.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02869"}},"official":{"repos":["cofe-ai/msg"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/tallrec-an-effective-and-efficient-tuning","slug":"tallrec-an-effective-and-efficient-tuning","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","date":"2023-04-30","arxiv_id":"2305.00447","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tallrec-an-effective-and-efficient-tuning#ran","syntology_url":"https://syntology.ai/paper/2305.00447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00447"}},"official":{"repos":["sai990323/tallrec"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unleashing-infinite-length-input-capacity-for","slug":"unleashing-infinite-length-input-capacity-for","title":"Enhancing Large Language Model with Self-Controlled Memory Framework","date":"2023-04-26","arxiv_id":"2304.13343","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"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) · 11 unverified","sample_list":"/paper/unleashing-infinite-length-input-capacity-for#ran","syntology_url":"https://syntology.ai/paper/2304.13343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13343"}},"official":{"repos":["wbbeyourself/scm4llms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/phoenix-democratizing-chatgpt-across","slug":"phoenix-democratizing-chatgpt-across","title":"Phoenix: Democratizing ChatGPT across Languages","date":"2023-04-20","arxiv_id":"2304.10453","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 3 unverified","sample_list":"/paper/phoenix-democratizing-chatgpt-across#ran","syntology_url":"https://syntology.ai/paper/2304.10453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10453"}},"official":{"repos":["freedomintelligence/llmzoo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rrhf-rank-responses-to-align-language-models","slug":"rrhf-rank-responses-to-align-language-models","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","date":"2023-04-11","arxiv_id":"2304.05302","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":2,"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/rrhf-rank-responses-to-align-language-models#ran","syntology_url":"https://syntology.ai/paper/2304.05302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05302"}},"official":{"repos":["ganjinzero/rrhf"],"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/generative-agents-interactive-simulacra-of","slug":"generative-agents-interactive-simulacra-of","title":"Generative Agents: Interactive Simulacra of Human Behavior","date":"2023-04-07","arxiv_id":"2304.03442","repositories_listed":8,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/generative-agents-interactive-simulacra-of#ran","syntology_url":"https://syntology.ai/paper/2304.03442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03442"}},"official":{"repos":["joonspk-research/generative_agents"],"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":["listed","official"]}}},{"url":"/paper/baize-an-open-source-chat-model-with","slug":"baize-an-open-source-chat-model-with","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","date":"2023-04-03","arxiv_id":"2304.01196","repositories_listed":5,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/baize-an-open-source-chat-model-with#ran","syntology_url":"https://syntology.ai/paper/2304.01196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01196"}},"official":{"repos":["project-baize/baize","project-baize/baize-chatbot"],"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"]}}},{"url":"/paper/camel-communicative-agents-for-mind","slug":"camel-communicative-agents-for-mind","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","date":"2023-03-31","arxiv_id":"2303.17760","repositories_listed":3,"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/camel-communicative-agents-for-mind#ran","syntology_url":"https://syntology.ai/paper/2303.17760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17760"}},"official":{"repos":["camel-ai/camel"],"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/wavcaps-a-chatgpt-assisted-weakly-labelled","slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","arxiv_id":"2303.17395","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled#ran","syntology_url":"https://syntology.ai/paper/2303.17395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17395"}},"official":{"repos":["xinhaomei/wavcaps"],"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/language-models-can-solve-computer-tasks","slug":"language-models-can-solve-computer-tasks","title":"Language Models can Solve Computer Tasks","date":"2023-03-30","arxiv_id":"2303.17491","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-can-solve-computer-tasks#ran","syntology_url":"https://syntology.ai/paper/2303.17491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17491"}},"official":{"repos":["posgnu/rci-agent"],"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/hallucinations-in-large-multilingual","slug":"hallucinations-in-large-multilingual","title":"Hallucinations in Large Multilingual Translation Models","date":"2023-03-28","arxiv_id":"2303.16104","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/hallucinations-in-large-multilingual#ran","syntology_url":"https://syntology.ai/paper/2303.16104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16104"}},"official":{"repos":["deep-spin/lmt_hallucinations"],"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/nl4opt-competition-formulating-optimization","slug":"nl4opt-competition-formulating-optimization","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","date":"2023-03-14","arxiv_id":"2303.08233","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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","sample_list":"/paper/nl4opt-competition-formulating-optimization#ran","syntology_url":"https://syntology.ai/paper/2303.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08233"}},"official":{"repos":["nl4opt/nl4opt-competition"],"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"]}}},{"url":"/paper/high-throughput-generative-inference-of-large","slug":"high-throughput-generative-inference-of-large","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","date":"2023-03-13","arxiv_id":"2303.06865","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/high-throughput-generative-inference-of-large#ran","syntology_url":"https://syntology.ai/paper/2303.06865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06865"}},"official":{"repos":["fminference/flexgen"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cost-effective-hyperparameter-optimization","slug":"cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","date":"2023-03-08","arxiv_id":"2303.04673","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/cost-effective-hyperparameter-optimization#ran","syntology_url":"https://syntology.ai/paper/2303.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04673"}},"official":{"repos":["microsoft/FLAML"],"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/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","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":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","sample_list":"/paper/prompting-large-language-models-with-answer#ran","syntology_url":"https://syntology.ai/paper/2303.01903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01903"}},"official":{"repos":["milvlg/prophet"],"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/what-makes-a-language-easy-to-deep-learn","slug":"what-makes-a-language-easy-to-deep-learn","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","date":"2023-02-23","arxiv_id":"2302.12239","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-makes-a-language-easy-to-deep-learn#ran","syntology_url":"https://syntology.ai/paper/2302.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12239"}},"official":{"repos":["lgalke/easy2deeplearn"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-independent-evaluation-of-chatgpt-on","slug":"an-independent-evaluation-of-chatgpt-on","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","date":"2023-02-23","arxiv_id":"2302.13814","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":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","sample_list":"/paper/an-independent-evaluation-of-chatgpt-on#ran","syntology_url":"https://syntology.ai/paper/2302.13814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13814"}},"official":{"repos":["lab-v2/chatgpt_mwp_eval"],"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/adaptive-test-generation-using-a-large","slug":"adaptive-test-generation-using-a-large","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","date":"2023-02-13","arxiv_id":"2302.06527","repositories_listed":2,"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":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","sample_list":"/paper/adaptive-test-generation-using-a-large#ran","syntology_url":"https://syntology.ai/paper/2302.06527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06527"}},"official":{"repos":["githubnext/testpilot"],"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/thoughtsource-a-central-hub-for-large","slug":"thoughtsource-a-central-hub-for-large","title":"ThoughtSource: A central hub for large language model reasoning data","date":"2023-01-27","arxiv_id":"2301.11596","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/thoughtsource-a-central-hub-for-large#ran","syntology_url":"https://syntology.ai/paper/2301.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11596"}},"official":{"repos":["openbiolink/thoughtsource"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/muse-text-to-image-generation-via-masked","slug":"muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","arxiv_id":"2301.00704","repositories_listed":5,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":8,"n_instrument":11,"n_unverified":2,"n_honours":2,"n_violates":5,"n_no_contract":1,"n_pointer_only":11,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/muse-text-to-image-generation-via-masked#ran","syntology_url":"https://syntology.ai/paper/2301.00704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00704"}},"official":null}},{"url":"/paper/soda-million-scale-dialogue-distillation-with","slug":"soda-million-scale-dialogue-distillation-with","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","date":"2022-12-20","arxiv_id":"2212.10465","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soda-million-scale-dialogue-distillation-with#ran","syntology_url":"https://syntology.ai/paper/2212.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10465"}},"official":{"repos":["skywalker023/sodaverse"],"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/parsel-a-unified-natural-language-framework","slug":"parsel-a-unified-natural-language-framework","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","date":"2022-12-20","arxiv_id":"2212.10561","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/parsel-a-unified-natural-language-framework#ran","syntology_url":"https://syntology.ai/paper/2212.10561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10561"}},"official":{"repos":["ezelikman/parsel"],"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/emergent-analogical-reasoning-in-large","slug":"emergent-analogical-reasoning-in-large","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","arxiv_id":"2212.09196","repositories_listed":2,"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/emergent-analogical-reasoning-in-large#ran","syntology_url":"https://syntology.ai/paper/2212.09196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09196"}},"official":{"repos":["taylorwwebb/emergent_analogies_llm"],"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/rethinking-the-role-of-scale-for-in-context","slug":"rethinking-the-role-of-scale-for-in-context","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","date":"2022-12-18","arxiv_id":"2212.09095","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-role-of-scale-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2212.09095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09095"}},"official":{"repos":["amazon-science/llm-interpret"],"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/on-second-thought-let-s-not-think-step-by","slug":"on-second-thought-let-s-not-think-step-by","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","date":"2022-12-15","arxiv_id":"2212.08061","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":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","sample_list":"/paper/on-second-thought-let-s-not-think-step-by#ran","syntology_url":"https://syntology.ai/paper/2212.08061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08061"}},"official":{"repos":["salt-nlp/chain-of-thought-bias"],"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/deepdfa-dataflow-analysis-guided-efficient","slug":"deepdfa-dataflow-analysis-guided-efficient","title":"Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection","date":"2022-12-15","arxiv_id":"2212.08108","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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) · 0 unverified","sample_list":"/paper/deepdfa-dataflow-analysis-guided-efficient#ran","syntology_url":"https://syntology.ai/paper/2212.08108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08108"}},"official":{"repos":["ISU-PAAL/DeepDFA"],"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/conal-anticipating-outliers-with-large","slug":"conal-anticipating-outliers-with-large","title":"Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models","date":"2022-11-28","arxiv_id":"2211.15718","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conal-anticipating-outliers-with-large#ran","syntology_url":"https://syntology.ai/paper/2211.15718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15718"}},"official":{"repos":["albertkx/conal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","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/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"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/arithmetic-sampling-parallel-diverse-decoding","slug":"arithmetic-sampling-parallel-diverse-decoding","title":"Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models","date":"2022-10-18","arxiv_id":"2210.15458","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/arithmetic-sampling-parallel-diverse-decoding#ran","syntology_url":"https://syntology.ai/paper/2210.15458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15458"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/attributed-text-generation-via-post-hoc","slug":"attributed-text-generation-via-post-hoc","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","date":"2022-10-17","arxiv_id":"2210.08726","repositories_listed":2,"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":2,"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/attributed-text-generation-via-post-hoc#ran","syntology_url":"https://syntology.ai/paper/2210.08726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08726"}},"official":{"repos":["anthonywchen/rarr"],"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/when-to-make-exceptions-exploring-language","slug":"when-to-make-exceptions-exploring-language","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","date":"2022-10-04","arxiv_id":"2210.01478","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/when-to-make-exceptions-exploring-language#ran","syntology_url":"https://syntology.ai/paper/2210.01478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01478"}},"official":{"repos":["feradauto/moralcot"],"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"]}}},{"url":"/paper/generate-rather-than-retrieve-large-language","slug":"generate-rather-than-retrieve-large-language","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","date":"2022-09-21","arxiv_id":"2209.10063","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generate-rather-than-retrieve-large-language#ran","syntology_url":"https://syntology.ai/paper/2209.10063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.10063"}},"official":{"repos":["wyu97/GenRead"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","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/prompting-as-probing-using-language-models#ran","syntology_url":"https://syntology.ai/paper/2208.11057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11057"}},"official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vault-augmenting-the-vision-and-language","slug":"vault-augmenting-the-vision-and-language","title":"VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media","date":"2022-08-18","arxiv_id":"2208.09021","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/vault-augmenting-the-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2208.09021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.09021"}},"official":{"repos":["gchochla/vault"],"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/housekeep-tidying-virtual-households-using","slug":"housekeep-tidying-virtual-households-using","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","date":"2022-05-22","arxiv_id":"2205.10712","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/housekeep-tidying-virtual-households-using#ran","syntology_url":"https://syntology.ai/paper/2205.10712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10712"}},"official":{"repos":["yashkant/housekeep"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-conversational-paradigm-for-program","slug":"a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","arxiv_id":"2203.13474","repositories_listed":8,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"10 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-conversational-paradigm-for-program#ran","syntology_url":"https://syntology.ai/paper/2203.13474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13474"}},"official":{"repos":["salesforce/CodeGen","salesforce/jaxformer"],"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":["listed","official"]}}},{"url":"/paper/zero-shot-image-to-text-generation-for-visual","slug":"zero-shot-image-to-text-generation-for-visual","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","date":"2021-11-29","arxiv_id":"2111.14447","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/zero-shot-image-to-text-generation-for-visual#ran","syntology_url":"https://syntology.ai/paper/2111.14447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14447"}},"official":{"repos":["yoadtew/zero-shot-image-to-text"],"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/raise-a-child-in-large-language-model-towards","slug":"raise-a-child-in-large-language-model-towards","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","date":"2021-09-13","arxiv_id":"2109.05687","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/raise-a-child-in-large-language-model-towards#ran","syntology_url":"https://syntology.ai/paper/2109.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05687"}},"official":{"repos":["alibaba/AliceMind","pkunlp-icler/childtuning"],"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"]}}}],"record_sha256":"41cad56c7beb857ffc189e693ddbf704612ad163a689325130a7909c719a4f3f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}