{"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/instruction-following/papers/ran/3","list_of":"/task/instruction-following","task":"Instruction Following","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":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":311,"counts":{"archive_papers_tagged":1135,"with_a_code_link":609,"where_syntology_ran_a_sample":311,"not_listed_spam_title":0,"listed":1135,"listed_where_code_ran":311,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":255,"every_run_a_failure_of_syntologys_instrument":56,"listed_with_a_run_with_no_instrument_failure":255,"listed_every_run_a_failure_of_syntologys_instrument":56,"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/instruction-following/papers/ran/1","prev":"/task/instruction-following/papers/ran/2","next":"/task/instruction-following/papers/ran/4","papers":[{"url":"/paper/solar-10-7b-scaling-large-language-models","slug":"solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","arxiv_id":"2312.15166","repositories_listed":2,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":17,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/solar-10-7b-scaling-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2312.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15166"}},"official":null}},{"url":"/paper/t-eval-evaluating-the-tool-utilization","slug":"t-eval-evaluating-the-tool-utilization","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","date":"2023-12-21","arxiv_id":"2312.14033","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/t-eval-evaluating-the-tool-utilization#ran","syntology_url":"https://syntology.ai/paper/2312.14033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14033"}},"official":{"repos":["open-compass/t-eval"],"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/an-in-depth-look-at-gemini-s-language","slug":"an-in-depth-look-at-gemini-s-language","title":"An In-depth Look at Gemini's Language Abilities","date":"2023-12-18","arxiv_id":"2312.11444","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/an-in-depth-look-at-gemini-s-language#ran","syntology_url":"https://syntology.ai/paper/2312.11444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11444"}},"official":{"repos":["neulab/gemini-benchmark"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m3dbench-let-s-instruct-large-models-with","slug":"m3dbench-let-s-instruct-large-models-with","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","date":"2023-12-17","arxiv_id":"2312.10763","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3dbench-let-s-instruct-large-models-with#ran","syntology_url":"https://syntology.ai/paper/2312.10763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10763"}},"official":{"repos":["OpenM3D/M3DBench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lmdrive-closed-loop-end-to-end-driving-with","slug":"lmdrive-closed-loop-end-to-end-driving-with","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","date":"2023-12-12","arxiv_id":"2312.07488","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lmdrive-closed-loop-end-to-end-driving-with#ran","syntology_url":"https://syntology.ai/paper/2312.07488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07488"}},"official":{"repos":["opendilab/lmdrive"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/localized-symbolic-knowledge-distillation-for-1","slug":"localized-symbolic-knowledge-distillation-for-1","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","date":"2023-12-08","arxiv_id":"2312.04837","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/localized-symbolic-knowledge-distillation-for-1#ran","syntology_url":"https://syntology.ai/paper/2312.04837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04837"}},"official":{"repos":["jamespark3922/localized-skd","jamespark3922/lskd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/creative-agents-empowering-agents-with","slug":"creative-agents-empowering-agents-with","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","date":"2023-12-05","arxiv_id":"2312.02519","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/creative-agents-empowering-agents-with#ran","syntology_url":"https://syntology.ai/paper/2312.02519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02519"}},"official":{"repos":["pku-rl/creative-agents"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"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/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/gift-generative-interpretable-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2312.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00700"}},"official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vim-probing-multimodal-large-language-models","slug":"vim-probing-multimodal-large-language-models","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","date":"2023-11-29","arxiv_id":"2311.17647","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":2,"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/vim-probing-multimodal-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.17647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17647"}},"official":{"repos":["vim-bench/vim_tool"],"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/ranni-taming-text-to-image-diffusion-for","slug":"ranni-taming-text-to-image-diffusion-for","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","date":"2023-11-28","arxiv_id":"2311.17002","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ranni-taming-text-to-image-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2311.17002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17002"}},"official":null}},{"url":"/paper/mods-model-oriented-data-selection-for","slug":"mods-model-oriented-data-selection-for","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","date":"2023-11-27","arxiv_id":"2311.15653","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":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mods-model-oriented-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2311.15653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15653"}},"official":{"repos":["casia-lm/mods"],"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/geochat-grounded-large-vision-language-model","slug":"geochat-grounded-large-vision-language-model","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","date":"2023-11-24","arxiv_id":"2311.15826","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/geochat-grounded-large-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2311.15826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15826"}},"official":{"repos":["mbzuai-oryx/geochat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/towards-improving-document-understanding-an","slug":"towards-improving-document-understanding-an","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","date":"2023-11-22","arxiv_id":"2311.13194","repositories_listed":1,"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":4,"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/towards-improving-document-understanding-an#ran","syntology_url":"https://syntology.ai/paper/2311.13194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13194"}},"official":{"repos":["harrytea/tgdoc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-instruction-optimization-for-open","slug":"automatic-instruction-optimization-for-open","title":"CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning","date":"2023-11-22","arxiv_id":"2311.13246","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automatic-instruction-optimization-for-open#ran","syntology_url":"https://syntology.ai/paper/2311.13246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13246"}},"official":{"repos":["lunyiliu/coachlm"],"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/hallucidoctor-mitigating-hallucinatory","slug":"hallucidoctor-mitigating-hallucinatory","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","date":"2023-11-22","arxiv_id":"2311.13614","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"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) · 6 unverified","sample_list":"/paper/hallucidoctor-mitigating-hallucinatory#ran","syntology_url":"https://syntology.ai/paper/2311.13614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13614"}},"official":{"repos":["yuqifan1117/hallucidoctor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/recexplainer-aligning-large-language-models","slug":"recexplainer-aligning-large-language-models","title":"RecExplainer: Aligning Large Language Models for Explaining Recommendation Models","date":"2023-11-18","arxiv_id":"2311.10947","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/recexplainer-aligning-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.10947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10947"}},"official":{"repos":["microsoft/recai"],"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/plug-leveraging-pivot-language-in-cross","slug":"plug-leveraging-pivot-language-in-cross","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","date":"2023-11-15","arxiv_id":"2311.08711","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/plug-leveraging-pivot-language-in-cross#ran","syntology_url":"https://syntology.ai/paper/2311.08711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08711"}},"official":{"repos":["ytyz1307zzh/plug"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-following-evaluation-for-large","slug":"instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","date":"2023-11-14","arxiv_id":"2311.07911","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/instruction-following-evaluation-for-large#ran","syntology_url":"https://syntology.ai/paper/2311.07911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07911"}},"official":{"repos":["google-research/google-research"],"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/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}},"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-evolved-diverse-data-sampling-for","slug":"self-evolved-diverse-data-sampling-for","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","date":"2023-11-14","arxiv_id":"2311.08182","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-evolved-diverse-data-sampling-for#ran","syntology_url":"https://syntology.ai/paper/2311.08182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08182"}},"official":{"repos":["ofa-sys/diverseevol"],"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/waterbench-towards-holistic-evaluation-of","slug":"waterbench-towards-holistic-evaluation-of","title":"WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models","date":"2023-11-13","arxiv_id":"2311.07138","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/waterbench-towards-holistic-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2311.07138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07138"}},"official":{"repos":["THU-KEG/WaterBench"],"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":["listed","official","unlocated"]}}},{"url":"/paper/cappy-outperforming-and-boosting-large-multi","slug":"cappy-outperforming-and-boosting-large-multi","title":"Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer","date":"2023-11-12","arxiv_id":"2311.06720","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/cappy-outperforming-and-boosting-large-multi#ran","syntology_url":"https://syntology.ai/paper/2311.06720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06720"}},"official":null}},{"url":"/paper/u-llava-unifying-multi-modal-tasks-via-large","slug":"u-llava-unifying-multi-modal-tasks-via-large","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","date":"2023-11-09","arxiv_id":"2311.05348","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/u-llava-unifying-multi-modal-tasks-via-large#ran","syntology_url":"https://syntology.ai/paper/2311.05348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05348"}},"official":{"repos":["OPPOMKLab/u-LLaVA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-plus-learning-to-use-tools-for-creating","slug":"llava-plus-learning-to-use-tools-for-creating","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","date":"2023-11-09","arxiv_id":"2311.05437","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/llava-plus-learning-to-use-tools-for-creating#ran","syntology_url":"https://syntology.ai/paper/2311.05437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05437"}},"official":{"repos":["LLaVA-VL/LLaVA-Plus-Codebase"],"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/language-models-are-super-mario-absorbing","slug":"language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","arxiv_id":"2311.03099","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/language-models-are-super-mario-absorbing#ran","syntology_url":"https://syntology.ai/paper/2311.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03099"}},"official":{"repos":["yule-buaa/mergelm"],"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/faithscore-evaluating-hallucinations-in-large","slug":"faithscore-evaluating-hallucinations-in-large","title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","date":"2023-11-02","arxiv_id":"2311.01477","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/faithscore-evaluating-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2311.01477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01477"}},"official":{"repos":["bcdnlp/faithscore"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/followbench-a-multi-level-fine-grained","slug":"followbench-a-multi-level-fine-grained","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","date":"2023-10-31","arxiv_id":"2310.20410","repositories_listed":1,"syntology":{"n":19,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/followbench-a-multi-level-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2310.20410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20410"}},"official":{"repos":["yjiangcm/followbench"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/myriad-large-multimodal-model-by-applying","slug":"myriad-large-multimodal-model-by-applying","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","date":"2023-10-29","arxiv_id":"2310.19070","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/myriad-large-multimodal-model-by-applying#ran","syntology_url":"https://syntology.ai/paper/2310.19070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19070"}},"official":{"repos":["tzjtatata/myriad"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/instruct-and-extract-instruction-tuning-for","slug":"instruct-and-extract-instruction-tuning-for","title":"Instruct and Extract: Instruction Tuning for On-Demand Information Extraction","date":"2023-10-24","arxiv_id":"2310.16040","repositories_listed":1,"syntology":{"n":21,"n_ran":12,"n_constructed":1,"n_ran_checked":11,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":21,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/instruct-and-extract-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2310.16040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16040"}},"official":{"repos":["yzjiao/on-demand-ie"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":11,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/alpacare-instruction-tuned-large-language","slug":"alpacare-instruction-tuned-large-language","title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","date":"2023-10-23","arxiv_id":"2310.14558","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":1,"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/alpacare-instruction-tuned-large-language#ran","syntology_url":"https://syntology.ai/paper/2310.14558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14558"}},"official":{"repos":["xzhang97666/alpacare"],"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/democratizing-reasoning-ability-tailored","slug":"democratizing-reasoning-ability-tailored","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","date":"2023-10-20","arxiv_id":"2310.13332","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/democratizing-reasoning-ability-tailored#ran","syntology_url":"https://syntology.ai/paper/2310.13332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13332"}},"official":{"repos":["raibows/learn-to-reason"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/botchat-evaluating-llms-capabilities-of","slug":"botchat-evaluating-llms-capabilities-of","title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues","date":"2023-10-20","arxiv_id":"2310.13650","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/botchat-evaluating-llms-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2310.13650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13650"}},"official":{"repos":["open-compass/botchat"],"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/lacma-language-aligning-contrastive-learning","slug":"lacma-language-aligning-contrastive-learning","title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","date":"2023-10-18","arxiv_id":"2310.12344","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/lacma-language-aligning-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2310.12344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12344"}},"official":{"repos":["joeyy5588/lacma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llark-a-multimodal-foundation-model-for-music","slug":"llark-a-multimodal-foundation-model-for-music","title":"LLark: A Multimodal Instruction-Following Language Model for Music","date":"2023-10-11","arxiv_id":"2310.07160","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"5 ran (of which 1 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/llark-a-multimodal-foundation-model-for-music#ran","syntology_url":"https://syntology.ai/paper/2310.07160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07160"}},"official":{"repos":["spotify-research/llark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/evaluating-large-language-models-at","slug":"evaluating-large-language-models-at","title":"Evaluating Large Language Models at Evaluating Instruction Following","date":"2023-10-11","arxiv_id":"2310.07641","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/evaluating-large-language-models-at#ran","syntology_url":"https://syntology.ai/paper/2310.07641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07641"}},"official":{"repos":["princeton-nlp/llmbar"],"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/how-abilities-in-large-language-models-are","slug":"how-abilities-in-large-language-models-are","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","date":"2023-10-09","arxiv_id":"2310.05492","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-abilities-in-large-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.05492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05492"}},"official":{"repos":["ofa-sys/gsm8k-screl"],"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/chat-vector-a-simple-approach-to-equip-llms","slug":"chat-vector-a-simple-approach-to-equip-llms","title":"Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages","date":"2023-10-07","arxiv_id":"2310.04799","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chat-vector-a-simple-approach-to-equip-llms#ran","syntology_url":"https://syntology.ai/paper/2310.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04799"}},"official":null}},{"url":"/paper/fool-your-vision-and-language-model-with","slug":"fool-your-vision-and-language-model-with","title":"Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations","date":"2023-10-02","arxiv_id":"2310.01651","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fool-your-vision-and-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2310.01651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01651"}},"official":{"repos":["ys-zong/foolyourvllms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/use-your-instinct-instruction-optimization","slug":"use-your-instinct-instruction-optimization","title":"Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers","date":"2023-10-02","arxiv_id":"2310.02905","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/use-your-instinct-instruction-optimization#ran","syntology_url":"https://syntology.ai/paper/2310.02905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02905"}},"official":{"repos":["xqlin98/INSTINCT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-task-performance-evaluating-and","slug":"beyond-task-performance-evaluating-and","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","date":"2023-10-01","arxiv_id":"2310.00647","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-task-performance-evaluating-and#ran","syntology_url":"https://syntology.ai/paper/2310.00647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00647"}},"official":{"repos":["mshukor/EvALign-ICL"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reformulating-vision-language-foundation","slug":"reformulating-vision-language-foundation","title":"Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants","date":"2023-10-01","arxiv_id":"2310.00653","repositories_listed":2,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reformulating-vision-language-foundation#ran","syntology_url":"https://syntology.ai/paper/2310.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00653"}},"official":{"repos":["thunlp/muffin"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/from-language-modeling-to-instruction","slug":"from-language-modeling-to-instruction","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","date":"2023-09-30","arxiv_id":"2310.00492","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-language-modeling-to-instruction#ran","syntology_url":"https://syntology.ai/paper/2310.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00492"}},"official":{"repos":["jacksonwuxs/interpret_instruction_tuning_llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/modulora-finetuning-3-bit-llms-on-consumer","slug":"modulora-finetuning-3-bit-llms-on-consumer","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","date":"2023-09-28","arxiv_id":"2309.16119","repositories_listed":3,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/modulora-finetuning-3-bit-llms-on-consumer#ran","syntology_url":"https://syntology.ai/paper/2309.16119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16119"}},"official":{"repos":["kuleshov-group/llmtools","kuleshov-group/modulora-experiment"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mentalllama-interpretable-mental-health","slug":"mentalllama-interpretable-mental-health","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","date":"2023-09-24","arxiv_id":"2309.13567","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":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/mentalllama-interpretable-mental-health#ran","syntology_url":"https://syntology.ai/paper/2309.13567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13567"}},"official":{"repos":["stevekgyang/mentallama","stevekgyang/mentalllama"],"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/longlora-efficient-fine-tuning-of-long","slug":"longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","arxiv_id":"2309.12307","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"11 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longlora-efficient-fine-tuning-of-long#ran","syntology_url":"https://syntology.ai/paper/2309.12307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12307"}},"official":{"repos":["dvlab-research/longlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/tegit-generating-high-quality-instruction","slug":"tegit-generating-high-quality-instruction","title":"DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping","date":"2023-09-11","arxiv_id":"2309.05447","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/tegit-generating-high-quality-instruction#ran","syntology_url":"https://syntology.ai/paper/2309.05447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05447"}},"official":{"repos":["bahuia/dog-instruct"],"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/are-emergent-abilities-in-large-language","slug":"are-emergent-abilities-in-large-language","title":"Are Emergent Abilities in Large Language Models just In-Context Learning?","date":"2023-09-04","arxiv_id":"2309.01809","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-emergent-abilities-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2309.01809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01809"}},"official":{"repos":["ukplab/on-emergence"],"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/point-bind-point-llm-aligning-point-cloud","slug":"point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":8,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/point-bind-point-llm-aligning-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2309.00615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00615"}},"official":{"repos":["ziyuguo99/point-bind_point-llm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sparkles-unlocking-chats-across-multiple","slug":"sparkles-unlocking-chats-across-multiple","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","date":"2023-08-31","arxiv_id":"2308.16463","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sparkles-unlocking-chats-across-multiple#ran","syntology_url":"https://syntology.ai/paper/2308.16463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16463"}},"official":{"repos":["hypjudy/sparkles"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llasm-large-language-and-speech-model","slug":"llasm-large-language-and-speech-model","title":"LLaSM: Large Language and Speech Model","date":"2023-08-30","arxiv_id":"2308.15930","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/llasm-large-language-and-speech-model#ran","syntology_url":"https://syntology.ai/paper/2308.15930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15930"}},"official":{"repos":["linksoul-ai/llasm"],"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/improving-translation-faithfulness-of-large","slug":"improving-translation-faithfulness-of-large","title":"Improving Translation Faithfulness of Large Language Models via Augmenting Instructions","date":"2023-08-24","arxiv_id":"2308.12674","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"8 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-translation-faithfulness-of-large#ran","syntology_url":"https://syntology.ai/paper/2308.12674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12674"}},"official":{"repos":["pppa2019/swie_overmiss_llm4mt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/code-llama-open-foundation-models-for-code","slug":"code-llama-open-foundation-models-for-code","title":"Code Llama: Open Foundation Models for Code","date":"2023-08-24","arxiv_id":"2308.12950","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/code-llama-open-foundation-models-for-code#ran","syntology_url":"https://syntology.ai/paper/2308.12950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12950"}},"official":{"repos":["facebookresearch/codellama"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/from-quantity-to-quality-boosting-llm","slug":"from-quantity-to-quality-boosting-llm","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","date":"2023-08-23","arxiv_id":"2308.12032","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-quantity-to-quality-boosting-llm#ran","syntology_url":"https://syntology.ai/paper/2308.12032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12032"}},"official":{"repos":["mingliiii/cherry_llm","tianyi-lab/cherry_llm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/instructiongpt-4-a-200-instruction-paradigm","slug":"instructiongpt-4-a-200-instruction-paradigm","title":"InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4","date":"2023-08-23","arxiv_id":"2308.12067","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/instructiongpt-4-a-200-instruction-paradigm#ran","syntology_url":"https://syntology.ai/paper/2308.12067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12067"}},"official":{"repos":["waltonfuture/InstructionGPT-4"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-position-matters-in-sequence","slug":"instruction-position-matters-in-sequence","title":"Instruction Position Matters in Sequence Generation with Large Language Models","date":"2023-08-23","arxiv_id":"2308.12097","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instruction-position-matters-in-sequence#ran","syntology_url":"https://syntology.ai/paper/2308.12097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12097"}},"official":{"repos":["adaxry/post-instruction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-you-really-follow-me-adversarial","slug":"do-you-really-follow-me-adversarial","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","date":"2023-08-17","arxiv_id":"2308.10819","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/do-you-really-follow-me-adversarial#ran","syntology_url":"https://syntology.ai/paper/2308.10819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10819"}},"official":{"repos":["leezekun/adv-instruct-eval","leezekun/instruction-following-robustness-eval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visit-bench-a-benchmark-for-vision-language","slug":"visit-bench-a-benchmark-for-vision-language","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","date":"2023-08-12","arxiv_id":"2308.06595","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visit-bench-a-benchmark-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.06595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06595"}},"official":{"repos":["mlfoundations/VisIT-Bench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-alignment-with-instruction","slug":"self-alignment-with-instruction","title":"Self-Alignment with Instruction Backtranslation","date":"2023-08-11","arxiv_id":"2308.06259","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-alignment-with-instruction#ran","syntology_url":"https://syntology.ai/paper/2308.06259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06259"}},"official":null}},{"url":"/paper/empowering-vision-language-models-to-follow","slug":"empowering-vision-language-models-to-follow","title":"Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions","date":"2023-08-08","arxiv_id":"2308.04152","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/empowering-vision-language-models-to-follow#ran","syntology_url":"https://syntology.ai/paper/2308.04152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04152"}},"official":{"repos":["dcdmllm/cheetah"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/agentbench-evaluating-llms-as-agents","slug":"agentbench-evaluating-llms-as-agents","title":"AgentBench: Evaluating LLMs as Agents","date":"2023-08-07","arxiv_id":"2308.03688","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agentbench-evaluating-llms-as-agents#ran","syntology_url":"https://syntology.ai/paper/2308.03688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03688"}},"official":{"repos":["thudm/agentbench"],"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/evaluating-correctness-and-faithfulness-of","slug":"evaluating-correctness-and-faithfulness-of","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","date":"2023-07-31","arxiv_id":"2307.16877","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evaluating-correctness-and-faithfulness-of#ran","syntology_url":"https://syntology.ai/paper/2307.16877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16877"}},"official":{"repos":["mcgill-nlp/instruct-qa"],"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/flask-fine-grained-language-model-evaluation","slug":"flask-fine-grained-language-model-evaluation","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","date":"2023-07-20","arxiv_id":"2307.10928","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":5,"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/flask-fine-grained-language-model-evaluation#ran","syntology_url":"https://syntology.ai/paper/2307.10928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10928"}},"official":{"repos":["kaistai/flask"],"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/l-eval-instituting-standardized-evaluation","slug":"l-eval-instituting-standardized-evaluation","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","date":"2023-07-20","arxiv_id":"2307.11088","repositories_listed":3,"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/l-eval-instituting-standardized-evaluation#ran","syntology_url":"https://syntology.ai/paper/2307.11088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11088"}},"official":{"repos":["openlmlab/leval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bubogpt-enabling-visual-grounding-in-multi","slug":"bubogpt-enabling-visual-grounding-in-multi","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","date":"2023-07-17","arxiv_id":"2307.08581","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/bubogpt-enabling-visual-grounding-in-multi#ran","syntology_url":"https://syntology.ai/paper/2307.08581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08581"}},"official":null}},{"url":"/paper/alpagasus-training-a-better-alpaca-with-fewer","slug":"alpagasus-training-a-better-alpaca-with-fewer","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","date":"2023-07-17","arxiv_id":"2307.08701","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alpagasus-training-a-better-alpaca-with-fewer#ran","syntology_url":"https://syntology.ai/paper/2307.08701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08701"}},"official":{"repos":["gpt4life/alpagasus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-emergent-abilities-exist-in-quantized","slug":"do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","arxiv_id":"2307.08072","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":14,"phrase":"12 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/do-emergent-abilities-exist-in-quantized#ran","syntology_url":"https://syntology.ai/paper/2307.08072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08072"}},"official":{"repos":["rucaibox/quantizedempirical"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-matters-in-training-a-gpt4-style","slug":"what-matters-in-training-a-gpt4-style","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","date":"2023-07-05","arxiv_id":"2307.02469","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-matters-in-training-a-gpt4-style#ran","syntology_url":"https://syntology.ai/paper/2307.02469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02469"}},"official":null}},{"url":"/paper/shifting-attention-to-relevance-towards-the","slug":"shifting-attention-to-relevance-towards-the","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","date":"2023-07-03","arxiv_id":"2307.01379","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shifting-attention-to-relevance-towards-the#ran","syntology_url":"https://syntology.ai/paper/2307.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01379"}},"official":{"repos":["jinhaoduan/sar","jinhaoduan/shifting-attention-to-relevance"],"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/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llavar-enhanced-visual-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17107"}},"official":{"repos":["SALT-NLP/LLaVAR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/on-the-exploitability-of-instruction-tuning-1","slug":"on-the-exploitability-of-instruction-tuning-1","title":"On the Exploitability of Instruction Tuning","date":"2023-06-28","arxiv_id":"2306.17194","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-the-exploitability-of-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2306.17194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17194"}},"official":{"repos":["azshue/autopoison"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/how-far-can-camels-go-exploring-the-state-of","slug":"how-far-can-camels-go-exploring-the-state-of","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","date":"2023-06-07","arxiv_id":"2306.04751","repositories_listed":4,"syntology":{"n":12,"n_ran":6,"n_constructed":1,"n_ran_checked":2,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/how-far-can-camels-go-exploring-the-state-of#ran","syntology_url":"https://syntology.ai/paper/2306.04751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04751"}},"official":{"repos":["allenai/open-instruct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/from-pixels-to-ui-actions-learning-to-follow","slug":"from-pixels-to-ui-actions-learning-to-follow","title":"From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces","date":"2023-05-31","arxiv_id":"2306.00245","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/from-pixels-to-ui-actions-learning-to-follow#ran","syntology_url":"https://syntology.ai/paper/2306.00245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00245"}},"official":{"repos":["google-deepmind/pix2act"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/navgpt-explicit-reasoning-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.16986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16986"}},"official":{"repos":["gengzezhou/navgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pandagpt-one-model-to-instruction-follow-them","slug":"pandagpt-one-model-to-instruction-follow-them","title":"PandaGPT: One Model To Instruction-Follow Them All","date":"2023-05-25","arxiv_id":"2305.16355","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pandagpt-one-model-to-instruction-follow-them#ran","syntology_url":"https://syntology.ai/paper/2305.16355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16355"}},"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/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/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","repositories_listed":20,"syntology":{"n":26,"n_ran":18,"n_constructed":1,"n_ran_checked":6,"n_instrument":12,"n_unverified":8,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/qlora-efficient-finetuning-of-quantized-llms#ran","syntology_url":"https://syntology.ai/paper/2305.14314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14314"}},"official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"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/llm-itself-can-read-and-generate-cxr-images","slug":"llm-itself-can-read-and-generate-cxr-images","title":"LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation","date":"2023-05-19","arxiv_id":"2305.11490","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/llm-itself-can-read-and-generate-cxr-images#ran","syntology_url":"https://syntology.ai/paper/2305.11490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11490"}},"official":{"repos":["hyn2028/llm-cxr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/caption-anything-interactive-image","slug":"caption-anything-interactive-image","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","date":"2023-05-04","arxiv_id":"2305.02677","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/caption-anything-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2305.02677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02677"}},"official":{"repos":["ttengwang/caption-anything"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"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/wizardlm-empowering-large-language-models-to","slug":"wizardlm-empowering-large-language-models-to","title":"WizardLM: Empowering Large Language Models to Follow Complex Instructions","date":"2023-04-24","arxiv_id":"2304.12244","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wizardlm-empowering-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2304.12244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12244"}},"official":{"repos":["nlpxucan/wizardlm"],"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/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","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/lana-a-language-capable-navigator-for","slug":"lana-a-language-capable-navigator-for","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","date":"2023-03-15","arxiv_id":"2303.08409","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":8,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 8 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) · 4 unverified","sample_list":"/paper/lana-a-language-capable-navigator-for#ran","syntology_url":"https://syntology.ai/paper/2303.08409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08409"}},"official":{"repos":["wxh1996/lana-vln"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":8,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cb2-collaborative-natural-language","slug":"cb2-collaborative-natural-language","title":"CB2: Collaborative Natural Language Interaction Research Platform","date":"2023-03-14","arxiv_id":"2303.08127","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":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cb2-collaborative-natural-language#ran","syntology_url":"https://syntology.ai/paper/2303.08127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08127"}},"official":{"repos":["lil-lab/cb2"],"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/in-context-instruction-learning","slug":"in-context-instruction-learning","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","date":"2023-02-28","arxiv_id":"2302.14691","repositories_listed":2,"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":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/in-context-instruction-learning#ran","syntology_url":"https://syntology.ai/paper/2302.14691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14691"}},"official":{"repos":["seonghyeonye/icil","seonghyeonye/tapp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/more-than-you-ve-asked-for-a-comprehensive","slug":"more-than-you-ve-asked-for-a-comprehensive","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","date":"2023-02-23","arxiv_id":"2302.12173","repositories_listed":2,"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/more-than-you-ve-asked-for-a-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2302.12173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12173"}},"official":{"repos":["greshake/llm-security","greshake/lm-safety"],"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/no-to-the-right-online-language-corrections","slug":"no-to-the-right-online-language-corrections","title":"\"No, to the Right\" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy","date":"2023-01-06","arxiv_id":"2301.02555","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/no-to-the-right-online-language-corrections#ran","syntology_url":"https://syntology.ai/paper/2301.02555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02555"}},"official":{"repos":["stanford-iliad/lilac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/precise-zero-shot-dense-retrieval-without","slug":"precise-zero-shot-dense-retrieval-without","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","date":"2022-12-20","arxiv_id":"2212.10496","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/precise-zero-shot-dense-retrieval-without#ran","syntology_url":"https://syntology.ai/paper/2212.10496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10496"}},"official":{"repos":["texttron/hyde"],"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/self-instruct-aligning-language-model-with","slug":"self-instruct-aligning-language-model-with","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","date":"2022-12-20","arxiv_id":"2212.10560","repositories_listed":19,"syntology":{"n":17,"n_ran":10,"n_constructed":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/self-instruct-aligning-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2212.10560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10560"}},"official":{"repos":["tatsu-lab/stanford_alpaca","yizhongw/self-instruct"],"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/continual-learning-for-instruction-following","slug":"continual-learning-for-instruction-following","title":"Continual Learning for Instruction Following from Realtime Feedback","date":"2022-12-19","arxiv_id":"2212.09710","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/continual-learning-for-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2212.09710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09710"}},"official":{"repos":["lil-lab/clif_cb"],"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/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/language-conditioned-reinforcement-learning","slug":"language-conditioned-reinforcement-learning","title":"Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections","date":"2022-11-18","arxiv_id":"2211.10168","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-conditioned-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2211.10168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10168"}},"official":{"repos":["frankroeder/lanro-gym"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-follow-instructions-in-text-based","slug":"learning-to-follow-instructions-in-text-based","title":"Learning to Follow Instructions in Text-Based Games","date":"2022-11-08","arxiv_id":"2211.04591","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/learning-to-follow-instructions-in-text-based#ran","syntology_url":"https://syntology.ai/paper/2211.04591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04591"}},"official":{"repos":["mathieutuli/ltl-gata"],"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/instruction-following-agents-with-jointly-pre","slug":"instruction-following-agents-with-jointly-pre","title":"Instruction-Following Agents with Multimodal Transformer","date":"2022-10-24","arxiv_id":"2210.13431","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/instruction-following-agents-with-jointly-pre#ran","syntology_url":"https://syntology.ai/paper/2210.13431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13431"}},"official":{"repos":["lhao499/instructrl"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/danli-deliberative-agent-for-following","slug":"danli-deliberative-agent-for-following","title":"DANLI: Deliberative Agent for Following Natural Language Instructions","date":"2022-10-22","arxiv_id":"2210.12485","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":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/danli-deliberative-agent-for-following#ran","syntology_url":"https://syntology.ai/paper/2210.12485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12485"}},"official":{"repos":["sled-group/danli"],"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/lm-nav-robotic-navigation-with-large-pre","slug":"lm-nav-robotic-navigation-with-large-pre","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","date":"2022-07-10","arxiv_id":"2207.04429","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lm-nav-robotic-navigation-with-large-pre#ran","syntology_url":"https://syntology.ai/paper/2207.04429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04429"}},"official":{"repos":["blazejosinski/lm_nav"],"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"]}}}],"record_sha256":"d5f6c6cfeab0c889eb623b0599d9b0592bf4e4b0a5d09b05d69c564a3f4a313a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}