{"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/2","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":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"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/1","next":"/task/instruction-following/papers/ran/3","papers":[{"url":"/paper/efficient-inference-of-vision-instruction","slug":"efficient-inference-of-vision-instruction","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","date":"2024-07-25","arxiv_id":"2407.18121","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-inference-of-vision-instruction#ran","syntology_url":"https://syntology.ai/paper/2407.18121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18121"}},"official":{"repos":["liuzuyan/elasticcache"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/primeguard-safe-and-helpful-llms-through","slug":"primeguard-safe-and-helpful-llms-through","title":"PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing","date":"2024-07-23","arxiv_id":"2407.16318","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/primeguard-safe-and-helpful-llms-through#ran","syntology_url":"https://syntology.ai/paper/2407.16318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16318"}},"official":{"repos":["dynamofl/primeguard"],"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/disco-embodied-navigation-and-interaction-via","slug":"disco-embodied-navigation-and-interaction-via","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","date":"2024-07-20","arxiv_id":"2407.14758","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disco-embodied-navigation-and-interaction-via#ran","syntology_url":"https://syntology.ai/paper/2407.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14758"}},"official":{"repos":["allenxuuu/disco"],"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/navgpt-2-unleashing-navigational-reasoning","slug":"navgpt-2-unleashing-navigational-reasoning","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","date":"2024-07-17","arxiv_id":"2407.12366","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/navgpt-2-unleashing-navigational-reasoning#ran","syntology_url":"https://syntology.ai/paper/2407.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12366"}},"official":{"repos":["gengzezhou/navgpt-2"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen2-audio-technical-report","slug":"qwen2-audio-technical-report","title":"Qwen2-Audio Technical Report","date":"2024-07-15","arxiv_id":"2407.10759","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qwen2-audio-technical-report#ran","syntology_url":"https://syntology.ai/paper/2407.10759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10759"}},"official":{"repos":["qwenlm/qwen2-audio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-loops-to-oops-fallback-behaviors-of","slug":"from-loops-to-oops-fallback-behaviors-of","title":"From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty","date":"2024-07-08","arxiv_id":"2407.06071","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-loops-to-oops-fallback-behaviors-of#ran","syntology_url":"https://syntology.ai/paper/2407.06071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06071"}},"official":{"repos":["mivg/fallbacks"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mmsci-a-multimodal-multi-discipline-dataset","slug":"mmsci-a-multimodal-multi-discipline-dataset","title":"MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding","date":"2024-07-06","arxiv_id":"2407.04903","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mmsci-a-multimodal-multi-discipline-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.04903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04903"}},"official":{"repos":["leezekun/mmsci"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/me-myself-and-ai-the-situational-awareness","slug":"me-myself-and-ai-the-situational-awareness","title":"Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs","date":"2024-07-05","arxiv_id":"2407.04694","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/me-myself-and-ai-the-situational-awareness#ran","syntology_url":"https://syntology.ai/paper/2407.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04694"}},"official":{"repos":["lrudl/sad"],"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/benchmarking-complex-instruction-following","slug":"benchmarking-complex-instruction-following","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","date":"2024-07-04","arxiv_id":"2407.03978","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-complex-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2407.03978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03978"}},"official":{"repos":["thu-coai/complexbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/funaudiollm-voice-understanding-and","slug":"funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","arxiv_id":"2407.04051","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funaudiollm-voice-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2407.04051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04051"}},"official":{"repos":["FunAudioLLM/SenseVoice","funaudiollm/cosyvoice"],"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":["listed","official"]}}},{"url":"/paper/the-sifo-benchmark-investigating-the","slug":"the-sifo-benchmark-investigating-the","title":"The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models","date":"2024-06-28","arxiv_id":"2406.19999","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-sifo-benchmark-investigating-the#ran","syntology_url":"https://syntology.ai/paper/2406.19999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19999"}},"official":{"repos":["shin-ee-chen/SIFo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/livebench-a-challenging-contamination-free","slug":"livebench-a-challenging-contamination-free","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","date":"2024-06-27","arxiv_id":"2406.19314","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/livebench-a-challenging-contamination-free#ran","syntology_url":"https://syntology.ai/paper/2406.19314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19314"}},"official":{"repos":["livebench/livebench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/suri-multi-constraint-instruction-following","slug":"suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","arxiv_id":"2406.19371","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suri-multi-constraint-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2406.19371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19371"}},"official":{"repos":["chtmp223/suri"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-space-knowledge-distillation-for-large","slug":"dual-space-knowledge-distillation-for-large","title":"Dual-Space Knowledge Distillation for Large Language Models","date":"2024-06-25","arxiv_id":"2406.17328","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/dual-space-knowledge-distillation-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.17328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17328"}},"official":{"repos":["songmzhang/dskd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lottery-ticket-adaptation-mitigating","slug":"lottery-ticket-adaptation-mitigating","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","date":"2024-06-24","arxiv_id":"2406.16797","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":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) · 1 unverified","sample_list":"/paper/lottery-ticket-adaptation-mitigating#ran","syntology_url":"https://syntology.ai/paper/2406.16797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16797"}},"official":{"repos":["kiddyboots216/lottery-ticket-adaptation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/res-q-evaluating-code-editing-large-language","slug":"res-q-evaluating-code-editing-large-language","title":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","date":"2024-06-24","arxiv_id":"2406.16801","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/res-q-evaluating-code-editing-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16801"}},"official":{"repos":["qurrent-ai/res-q"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/audiobench-a-universal-benchmark-for-audio","slug":"audiobench-a-universal-benchmark-for-audio","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","date":"2024-06-23","arxiv_id":"2406.16020","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/audiobench-a-universal-benchmark-for-audio#ran","syntology_url":"https://syntology.ai/paper/2406.16020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16020"}},"official":{"repos":["audiollms/audiobench"],"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/iwisdm-assessing-instruction-following-in","slug":"iwisdm-assessing-instruction-following-in","title":"IWISDM: Assessing instruction following in multimodal models at scale","date":"2024-06-20","arxiv_id":"2406.14343","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/iwisdm-assessing-instruction-following-in#ran","syntology_url":"https://syntology.ai/paper/2406.14343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14343"}},"official":{"repos":["bashivanlab/iwisdm"],"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/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llasa-large-multimodal-agent-for-human#ran","syntology_url":"https://syntology.ai/paper/2406.14498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14498"}},"official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/biomedical-visual-instruction-tuning-with","slug":"biomedical-visual-instruction-tuning-with","title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment","date":"2024-06-19","arxiv_id":"2406.13173","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/biomedical-visual-instruction-tuning-with#ran","syntology_url":"https://syntology.ai/paper/2406.13173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13173"}},"official":{"repos":["mao1207/BioMed-VITAL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-play-with-execution-feedback-improving","slug":"self-play-with-execution-feedback-improving","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","date":"2024-06-19","arxiv_id":"2406.13542","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-play-with-execution-feedback-improving#ran","syntology_url":"https://syntology.ai/paper/2406.13542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13542"}},"official":{"repos":["QwenLM/AutoIF"],"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/snap-unlearning-selective-knowledge-in-large","slug":"snap-unlearning-selective-knowledge-in-large","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","date":"2024-06-18","arxiv_id":"2406.12329","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/snap-unlearning-selective-knowledge-in-large#ran","syntology_url":"https://syntology.ai/paper/2406.12329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12329"}},"official":{"repos":["brightjade/Opt-Out","brightjade/snap-unlearning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/chatglm-a-family-of-large-language-models","slug":"chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","arxiv_id":"2406.12793","repositories_listed":7,"syntology":{"n":29,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/chatglm-a-family-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.12793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12793"}},"official":{"repos":["thudm/chatglm-6b"],"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":["listed","official"]}}},{"url":"/paper/refusal-in-language-models-is-mediated-by-a","slug":"refusal-in-language-models-is-mediated-by-a","title":"Refusal in Language Models Is Mediated by a Single Direction","date":"2024-06-17","arxiv_id":"2406.11717","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/refusal-in-language-models-is-mediated-by-a#ran","syntology_url":"https://syntology.ai/paper/2406.11717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11717"}},"official":{"repos":["andyrdt/refusal_direction"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/chatbug-a-common-vulnerability-of-aligned","slug":"chatbug-a-common-vulnerability-of-aligned","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","date":"2024-06-17","arxiv_id":"2406.12935","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/chatbug-a-common-vulnerability-of-aligned#ran","syntology_url":"https://syntology.ai/paper/2406.12935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12935"}},"official":{"repos":["uw-nsl/ChatBug"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/milora-harnessing-minor-singular-components","slug":"milora-harnessing-minor-singular-components","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","date":"2024-06-13","arxiv_id":"2406.09044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/milora-harnessing-minor-singular-components#ran","syntology_url":"https://syntology.ai/paper/2406.09044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09044"}},"official":{"repos":["graphpku/pissa"],"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/unpacking-dpo-and-ppo-disentangling-best","slug":"unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","arxiv_id":"2406.09279","repositories_listed":2,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/unpacking-dpo-and-ppo-disentangling-best#ran","syntology_url":"https://syntology.ai/paper/2406.09279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09279"}},"official":{"repos":["allenai/open-instruct","hamishivi/easylm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/taste-teaching-large-language-models-to","slug":"taste-teaching-large-language-models-to","title":"TasTe: Teaching Large Language Models to Translate through Self-Reflection","date":"2024-06-12","arxiv_id":"2406.08434","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/taste-teaching-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2406.08434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08434"}},"official":{"repos":["yutongwang1216/reflectionllmmt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rs-agent-automating-remote-sensing-tasks","slug":"rs-agent-automating-remote-sensing-tasks","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","date":"2024-06-11","arxiv_id":"2406.07089","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rs-agent-automating-remote-sensing-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.07089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07089"}},"official":{"repos":["intellisensing/rs-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-biggen-bench-a-principled-benchmark-for","slug":"the-biggen-bench-a-principled-benchmark-for","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","date":"2024-06-09","arxiv_id":"2406.05761","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-biggen-bench-a-principled-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.05761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05761"}},"official":{"repos":["prometheus-eval/prometheus-eval"],"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/corda-context-oriented-decomposition","slug":"corda-context-oriented-decomposition","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","date":"2024-06-07","arxiv_id":"2406.05223","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/corda-context-oriented-decomposition#ran","syntology_url":"https://syntology.ai/paper/2406.05223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05223"}},"official":{"repos":["iboing/corda"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/blsp-emo-towards-empathetic-large-speech","slug":"blsp-emo-towards-empathetic-large-speech","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","date":"2024-06-06","arxiv_id":"2406.03872","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blsp-emo-towards-empathetic-large-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03872"}},"official":{"repos":["cwang621/blsp-emo"],"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/interactive-text-to-image-retrieval-with","slug":"interactive-text-to-image-retrieval-with","title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","date":"2024-06-05","arxiv_id":"2406.03411","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/interactive-text-to-image-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2406.03411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03411"}},"official":{"repos":["saehyung-lee/plugir"],"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/phased-instruction-fine-tuning-for-large","slug":"phased-instruction-fine-tuning-for-large","title":"Phased Instruction Fine-Tuning for Large Language Models","date":"2024-06-01","arxiv_id":"2406.04371","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/phased-instruction-fine-tuning-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04371"}},"official":{"repos":["xubuvd/phasedsft"],"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/x-instruction-aligning-language-model-in-low","slug":"x-instruction-aligning-language-model-in-low","title":"X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions","date":"2024-05-30","arxiv_id":"2405.19744","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/x-instruction-aligning-language-model-in-low#ran","syntology_url":"https://syntology.ai/paper/2405.19744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19744"}},"official":{"repos":["znlp/x-instruction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-guided-visual-masking","slug":"instruction-guided-visual-masking","title":"Instruction-Guided Visual Masking","date":"2024-05-30","arxiv_id":"2405.19783","repositories_listed":1,"syntology":{"n":28,"n_ran":20,"n_constructed":7,"n_ran_checked":11,"n_instrument":9,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"20 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/instruction-guided-visual-masking#ran","syntology_url":"https://syntology.ai/paper/2405.19783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19783"}},"official":{"repos":["2toinf/ivm"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":7,"n_ran_no_instrument_failure":11,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/is-in-context-learning-sufficient-for","slug":"is-in-context-learning-sufficient-for","title":"Is In-Context Learning Sufficient for Instruction Following in LLMs?","date":"2024-05-30","arxiv_id":"2405.19874","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/is-in-context-learning-sufficient-for#ran","syntology_url":"https://syntology.ai/paper/2405.19874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19874"}},"official":{"repos":["tml-epfl/icl-alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/weak-to-strong-search-align-large-language","slug":"weak-to-strong-search-align-large-language","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","date":"2024-05-29","arxiv_id":"2405.19262","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 1 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/weak-to-strong-search-align-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.19262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19262"}},"official":{"repos":["zhziszz/weak-to-strong-search"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-exploring-language-models-active","slug":"self-exploring-language-models-active","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","date":"2024-05-29","arxiv_id":"2405.19332","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-exploring-language-models-active#ran","syntology_url":"https://syntology.ai/paper/2405.19332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19332"}},"official":{"repos":["shenao-zhang/selm"],"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/mathchat-benchmarking-mathematical-reasoning","slug":"mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","arxiv_id":"2405.19444","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/mathchat-benchmarking-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2405.19444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19444"}},"official":{"repos":["zhenwen-nlp/mathchat"],"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/promptfix-you-prompt-and-we-fix-the-photo","slug":"promptfix-you-prompt-and-we-fix-the-photo","title":"PromptFix: You Prompt and We Fix the Photo","date":"2024-05-27","arxiv_id":"2405.16785","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/promptfix-you-prompt-and-we-fix-the-photo#ran","syntology_url":"https://syntology.ai/paper/2405.16785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16785"}},"official":{"repos":["yeates/promptfix"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/simpo-simple-preference-optimization-with-a","slug":"simpo-simple-preference-optimization-with-a","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","date":"2024-05-23","arxiv_id":"2405.14734","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpo-simple-preference-optimization-with-a#ran","syntology_url":"https://syntology.ai/paper/2405.14734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14734"}},"official":{"repos":["princeton-nlp/simpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/editworld-simulating-world-dynamics-for","slug":"editworld-simulating-world-dynamics-for","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","date":"2024-05-23","arxiv_id":"2405.14785","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":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/editworld-simulating-world-dynamics-for#ran","syntology_url":"https://syntology.ai/paper/2405.14785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14785"}},"official":{"repos":["yangling0818/editworld"],"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/disperse-then-merge-pushing-the-limits-of","slug":"disperse-then-merge-pushing-the-limits-of","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","date":"2024-05-22","arxiv_id":"2405.13432","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/disperse-then-merge-pushing-the-limits-of#ran","syntology_url":"https://syntology.ai/paper/2405.13432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13432"}},"official":{"repos":["TingchenFu/ACL24-ExpertFusion"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-3d-llm-with-referent-tokens","slug":"grounded-3d-llm-with-referent-tokens","title":"Grounded 3D-LLM with Referent Tokens","date":"2024-05-16","arxiv_id":"2405.10370","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"13 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/grounded-3d-llm-with-referent-tokens#ran","syntology_url":"https://syntology.ai/paper/2405.10370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10370"}},"official":{"repos":["OpenRobotLab/Grounded_3D-LLM"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-safety-realignment-framework-via-subspace","slug":"a-safety-realignment-framework-via-subspace","title":"A safety realignment framework via subspace-oriented model fusion for large language models","date":"2024-05-15","arxiv_id":"2405.09055","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/a-safety-realignment-framework-via-subspace#ran","syntology_url":"https://syntology.ai/paper/2405.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09055"}},"official":{"repos":["xinykou/safety_realignment"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-instruction-following-in-language","slug":"improving-instruction-following-in-language","title":"Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation","date":"2024-05-10","arxiv_id":"2405.06424","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-instruction-following-in-language#ran","syntology_url":"https://syntology.ai/paper/2405.06424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06424"}},"official":{"repos":["p-b-u/proxy_based_uncertainty"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"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, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}},"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-llm-guided-counterfactual","slug":"zero-shot-llm-guided-counterfactual","title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","date":"2024-05-08","arxiv_id":"2405.04793","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/zero-shot-llm-guided-counterfactual#ran","syntology_url":"https://syntology.ai/paper/2405.04793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04793"}},"official":{"repos":["AmritaBh/zero-shot-llm-counterfactual"],"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/from-complex-to-simple-enhancing-multi","slug":"from-complex-to-simple-enhancing-multi","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","date":"2024-04-24","arxiv_id":"2404.15846","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/from-complex-to-simple-enhancing-multi#ran","syntology_url":"https://syntology.ai/paper/2404.15846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15846"}},"official":{"repos":["meowpass/followcomplexinstruction"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/meddr-diagnosis-guided-bootstrapping-for","slug":"meddr-diagnosis-guided-bootstrapping-for","title":"GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration","date":"2024-04-23","arxiv_id":"2404.15127","repositories_listed":1,"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/meddr-diagnosis-guided-bootstrapping-for#ran","syntology_url":"https://syntology.ai/paper/2404.15127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15127"}},"official":{"repos":["sunanhe/meddr"],"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/teaching-llama-a-new-language-through-cross","slug":"teaching-llama-a-new-language-through-cross","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","date":"2024-04-05","arxiv_id":"2404.04042","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/teaching-llama-a-new-language-through-cross#ran","syntology_url":"https://syntology.ai/paper/2404.04042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04042"}},"official":{"repos":["tartunlp/llammas"],"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/evaluating-llms-at-detecting-errors-in-llm","slug":"evaluating-llms-at-detecting-errors-in-llm","title":"Evaluating LLMs at Detecting Errors in LLM Responses","date":"2024-04-04","arxiv_id":"2404.03602","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evaluating-llms-at-detecting-errors-in-llm#ran","syntology_url":"https://syntology.ai/paper/2404.03602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03602"}},"official":{"repos":["psunlpgroup/realmistake"],"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/conifer-improving-complex-constrained","slug":"conifer-improving-complex-constrained","title":"Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models","date":"2024-04-03","arxiv_id":"2404.02823","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/conifer-improving-complex-constrained#ran","syntology_url":"https://syntology.ai/paper/2404.02823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02823"}},"official":{"repos":["coniferlm/conifer"],"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/learning-by-correction-efficient-tuning-task","slug":"learning-by-correction-efficient-tuning-task","title":"Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning","date":"2024-04-01","arxiv_id":"2404.00909","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-by-correction-efficient-tuning-task#ran","syntology_url":"https://syntology.ai/paper/2404.00909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00909"}},"official":{"repos":["shtuplus/iccc_cvpr2024"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/direct-preference-optimization-of-video-large","slug":"direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","arxiv_id":"2404.01258","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-optimization-of-video-large#ran","syntology_url":"https://syntology.ai/paper/2404.01258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01258"}},"official":{"repos":["riflezhang/llava-hound-dpo"],"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/coda-constrained-generation-based-data","slug":"coda-constrained-generation-based-data","title":"CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP","date":"2024-03-30","arxiv_id":"2404.00415","repositories_listed":1,"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":8,"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/coda-constrained-generation-based-data#ran","syntology_url":"https://syntology.ai/paper/2404.00415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00415"}},"official":{"repos":["sreyan88/coda"],"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/top-leaderboard-ranking-top-coding","slug":"top-leaderboard-ranking-top-coding","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","date":"2024-03-28","arxiv_id":"2403.19114","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":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/top-leaderboard-ranking-top-coding#ran","syntology_url":"https://syntology.ai/paper/2403.19114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19114"}},"official":{"repos":["evo-eval/evoeval"],"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/lita-language-instructed-temporal","slug":"lita-language-instructed-temporal","title":"LITA: Language Instructed Temporal-Localization Assistant","date":"2024-03-27","arxiv_id":"2403.19046","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lita-language-instructed-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.19046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19046"}},"official":{"repos":["nvlabs/lita"],"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/flashface-human-image-personalization-with","slug":"flashface-human-image-personalization-with","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","date":"2024-03-25","arxiv_id":"2403.17008","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 8 unverified","sample_list":"/paper/flashface-human-image-personalization-with#ran","syntology_url":"https://syntology.ai/paper/2403.17008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17008"}},"official":null}},{"url":"/paper/chain-of-spot-interactive-reasoning-improves","slug":"chain-of-spot-interactive-reasoning-improves","title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","date":"2024-03-19","arxiv_id":"2403.12966","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chain-of-spot-interactive-reasoning-improves#ran","syntology_url":"https://syntology.ai/paper/2403.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12966"}},"official":{"repos":["dongyh20/chain-of-spot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/minedreamer-learning-to-follow-instructions","slug":"minedreamer-learning-to-follow-instructions","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","date":"2024-03-18","arxiv_id":"2403.12037","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minedreamer-learning-to-follow-instructions#ran","syntology_url":"https://syntology.ai/paper/2403.12037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12037"}},"official":{"repos":["Zhoues/MineDreamer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/coin-a-benchmark-of-continual-instruction","slug":"coin-a-benchmark-of-continual-instruction","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","date":"2024-03-13","arxiv_id":"2403.08350","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coin-a-benchmark-of-continual-instruction#ran","syntology_url":"https://syntology.ai/paper/2403.08350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08350"}},"official":{"repos":["zackschen/coin"],"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/aligners-decoupling-llms-and-alignment","slug":"aligners-decoupling-llms-and-alignment","title":"Aligners: Decoupling LLMs and Alignment","date":"2024-03-07","arxiv_id":"2403.04224","repositories_listed":2,"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/aligners-decoupling-llms-and-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.04224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04224"}},"official":{"repos":["lilianngweta/aligners-and-inspectors","lilianngweta/aligners"],"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/learning-to-decode-collaboratively-with","slug":"learning-to-decode-collaboratively-with","title":"Learning to Decode Collaboratively with Multiple Language Models","date":"2024-03-06","arxiv_id":"2403.03870","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":6,"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/learning-to-decode-collaboratively-with#ran","syntology_url":"https://syntology.ai/paper/2403.03870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03870"}},"official":{"repos":["clinicalml/co-llm"],"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/lab-large-scale-alignment-for-chatbots","slug":"lab-large-scale-alignment-for-chatbots","title":"LAB: Large-Scale Alignment for ChatBots","date":"2024-03-02","arxiv_id":"2403.01081","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lab-large-scale-alignment-for-chatbots#ran","syntology_url":"https://syntology.ai/paper/2403.01081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01081"}},"official":null}},{"url":"/paper/autodefense-multi-agent-llm-defense-against","slug":"autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","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/autodefense-multi-agent-llm-defense-against#ran","syntology_url":"https://syntology.ai/paper/2403.04783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04783"}},"official":{"repos":["xhmy/autodefense"],"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/songcomposer-a-large-language-model-for-lyric","slug":"songcomposer-a-large-language-model-for-lyric","title":"SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition","date":"2024-02-27","arxiv_id":"2402.17645","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/songcomposer-a-large-language-model-for-lyric#ran","syntology_url":"https://syntology.ai/paper/2402.17645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17645"}},"official":{"repos":["pjlab-songcomposer/songcomposer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"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":["listed","official"]}}},{"url":"/paper/follow-my-instruction-and-spill-the-beans","slug":"follow-my-instruction-and-spill-the-beans","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","date":"2024-02-27","arxiv_id":"2402.17840","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/follow-my-instruction-and-spill-the-beans#ran","syntology_url":"https://syntology.ai/paper/2402.17840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17840"}},"official":{"repos":["zhentingqi/rag-privacy"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/long-context-language-modeling-with-parallel","slug":"long-context-language-modeling-with-parallel","title":"Long-Context Language Modeling with Parallel Context Encoding","date":"2024-02-26","arxiv_id":"2402.16617","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/long-context-language-modeling-with-parallel#ran","syntology_url":"https://syntology.ai/paper/2402.16617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16617"}},"official":{"repos":["princeton-nlp/cepe"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/graphwiz-an-instruction-following-language","slug":"graphwiz-an-instruction-following-language","title":"GraphWiz: An Instruction-Following Language Model for Graph Problems","date":"2024-02-25","arxiv_id":"2402.16029","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/graphwiz-an-instruction-following-language#ran","syntology_url":"https://syntology.ai/paper/2402.16029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16029"}},"official":{"repos":["nuochenpku/Graph-Reasoning-LLM"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/defending-large-language-models-against-1","slug":"defending-large-language-models-against-1","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","date":"2024-02-25","arxiv_id":"2402.16192","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/defending-large-language-models-against-1#ran","syntology_url":"https://syntology.ai/paper/2402.16192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16192"}},"official":{"repos":["ucsb-nlp-chang/semanticsmooth"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-multi-turn-instruction-following-for","slug":"on-the-multi-turn-instruction-following-for","title":"On the Multi-turn Instruction Following for Conversational Web Agents","date":"2024-02-23","arxiv_id":"2402.15057","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/on-the-multi-turn-instruction-following-for#ran","syntology_url":"https://syntology.ai/paper/2402.15057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15057"}},"official":{"repos":["magicgh/self-map"],"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/instraug-automatic-instruction-augmentation","slug":"instraug-automatic-instruction-augmentation","title":"Towards Robust Instruction Tuning on Multimodal Large Language Models","date":"2024-02-22","arxiv_id":"2402.14492","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instraug-automatic-instruction-augmentation#ran","syntology_url":"https://syntology.ai/paper/2402.14492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14492"}},"official":{"repos":["declare-lab/instraug"],"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/unintended-impacts-of-llm-alignment-on-global","slug":"unintended-impacts-of-llm-alignment-on-global","title":"Unintended Impacts of LLM Alignment on Global Representation","date":"2024-02-22","arxiv_id":"2402.15018","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/unintended-impacts-of-llm-alignment-on-global#ran","syntology_url":"https://syntology.ai/paper/2402.15018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15018"}},"official":{"repos":["salt-nlp/unintended-impacts-of-alignment"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/self-distillation-bridges-distribution-gap-in","slug":"self-distillation-bridges-distribution-gap-in","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","date":"2024-02-21","arxiv_id":"2402.13669","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-distillation-bridges-distribution-gap-in#ran","syntology_url":"https://syntology.ai/paper/2402.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13669"}},"official":{"repos":["sail-sg/sdft"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/promptkd-distilling-student-friendly","slug":"promptkd-distilling-student-friendly","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","date":"2024-02-20","arxiv_id":"2402.12842","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/promptkd-distilling-student-friendly#ran","syntology_url":"https://syntology.ai/paper/2402.12842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12842"}},"official":{"repos":["gmkim-ai/promptkd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-are-homer-simpson-safety-re","slug":"language-models-are-homer-simpson-safety-re","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","date":"2024-02-19","arxiv_id":"2402.11746","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":9,"phrase":"13 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/language-models-are-homer-simpson-safety-re#ran","syntology_url":"https://syntology.ai/paper/2402.11746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11746"}},"official":{"repos":["declare-lab/resta","hiyouga/llama-factory"],"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":["listed","official"]}}},{"url":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-critical-evaluation-of-ai-feedback-for#ran","syntology_url":"https://syntology.ai/paper/2402.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12366"}},"official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/your-vision-language-model-itself-is-a-strong","slug":"your-vision-language-model-itself-is-a-strong","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","date":"2024-02-19","arxiv_id":"2402.12501","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/your-vision-language-model-itself-is-a-strong#ran","syntology_url":"https://syntology.ai/paper/2402.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12501"}},"official":{"repos":["rayruibochen/self-filter"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-modalities-in-vision-large-language","slug":"aligning-modalities-in-vision-large-language","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","date":"2024-02-18","arxiv_id":"2402.11411","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-modalities-in-vision-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.11411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11411"}},"official":{"repos":["yiyangzhou/povid"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-large-language-models-by-on-policy","slug":"aligning-large-language-models-by-on-policy","title":"Aligning Large Language Models by On-Policy Self-Judgment","date":"2024-02-17","arxiv_id":"2402.11253","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":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/aligning-large-language-models-by-on-policy#ran","syntology_url":"https://syntology.ai/paper/2402.11253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11253"}},"official":{"repos":["oddqueue/self-judge"],"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/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/answer-is-all-you-need-instruction-following","slug":"answer-is-all-you-need-instruction-following","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","date":"2024-02-15","arxiv_id":"2402.09642","repositories_listed":1,"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/answer-is-all-you-need-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2402.09642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09642"}},"official":{"repos":["zhang-yu-wei/inbedder"],"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/selective-reflection-tuning-student-selected","slug":"selective-reflection-tuning-student-selected","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","date":"2024-02-15","arxiv_id":"2402.10110","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selective-reflection-tuning-student-selected#ran","syntology_url":"https://syntology.ai/paper/2402.10110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10110"}},"official":{"repos":["tianyi-lab/reflection_tuning"],"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/policy-improvement-using-language-feedback","slug":"policy-improvement-using-language-feedback","title":"Policy Improvement using Language Feedback Models","date":"2024-02-12","arxiv_id":"2402.07876","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-improvement-using-language-feedback#ran","syntology_url":"https://syntology.ai/paper/2402.07876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07876"}},"official":{"repos":["vzhong/language_feedback_models"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graphtranslator-aligning-graph-model-to-large","slug":"graphtranslator-aligning-graph-model-to-large","title":"GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks","date":"2024-02-11","arxiv_id":"2402.07197","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graphtranslator-aligning-graph-model-to-large#ran","syntology_url":"https://syntology.ai/paper/2402.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07197"}},"official":{"repos":["alibaba/graphtranslator"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-es-gradient-free-planning-with","slug":"diffusion-es-gradient-free-planning-with","title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following","date":"2024-02-09","arxiv_id":"2402.06559","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diffusion-es-gradient-free-planning-with#ran","syntology_url":"https://syntology.ai/paper/2402.06559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06559"}},"official":{"repos":["bhyang/diffusion-es"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/distillm-towards-streamlined-distillation-for","slug":"distillm-towards-streamlined-distillation-for","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","date":"2024-02-06","arxiv_id":"2402.03898","repositories_listed":5,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distillm-towards-streamlined-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2402.03898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03898"}},"official":{"repos":["jongwooko/distillm"],"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":["found_in_text","listed","official"]}}},{"url":"/paper/personalized-language-modeling-from","slug":"personalized-language-modeling-from","title":"Personalized Language Modeling from Personalized Human Feedback","date":"2024-02-06","arxiv_id":"2402.05133","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/personalized-language-modeling-from#ran","syntology_url":"https://syntology.ai/paper/2402.05133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05133"}},"official":{"repos":["humainlab/personalized_rlhf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safety-fine-tuning-at-almost-no-cost-a","slug":"safety-fine-tuning-at-almost-no-cost-a","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","date":"2024-02-03","arxiv_id":"2402.02207","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/safety-fine-tuning-at-almost-no-cost-a#ran","syntology_url":"https://syntology.ai/paper/2402.02207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02207"}},"official":{"repos":["ys-zong/vlguard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/longalign-a-recipe-for-long-context-alignment","slug":"longalign-a-recipe-for-long-context-alignment","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","date":"2024-01-31","arxiv_id":"2401.18058","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/longalign-a-recipe-for-long-context-alignment#ran","syntology_url":"https://syntology.ai/paper/2401.18058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.18058"}},"official":{"repos":["thudm/longalign"],"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/towards-3d-molecule-text-interpretation-in","slug":"towards-3d-molecule-text-interpretation-in","title":"Towards 3D Molecule-Text Interpretation in Language Models","date":"2024-01-25","arxiv_id":"2401.13923","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-3d-molecule-text-interpretation-in#ran","syntology_url":"https://syntology.ai/paper/2401.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13923"}},"official":{"repos":["lsh0520/3d-molm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-rewarding-language-models","slug":"self-rewarding-language-models","title":"Self-Rewarding Language Models","date":"2024-01-18","arxiv_id":"2401.10020","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":3,"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, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/self-rewarding-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.10020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10020"}},"official":null}},{"url":"/paper/emollms-a-series-of-emotional-large-language","slug":"emollms-a-series-of-emotional-large-language","title":"EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis","date":"2024-01-16","arxiv_id":"2401.08508","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emollms-a-series-of-emotional-large-language#ran","syntology_url":"https://syntology.ai/paper/2401.08508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08508"}},"official":{"repos":["lzw108/emollms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/infobench-evaluating-instruction-following","slug":"infobench-evaluating-instruction-following","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","date":"2024-01-07","arxiv_id":"2401.03601","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/infobench-evaluating-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2401.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03601"}},"official":{"repos":["qinyiwei/infobench"],"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/chartassisstant-a-universal-chart-multimodal","slug":"chartassisstant-a-universal-chart-multimodal","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","date":"2024-01-04","arxiv_id":"2401.02384","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/chartassisstant-a-universal-chart-multimodal#ran","syntology_url":"https://syntology.ai/paper/2401.02384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02384"}},"official":{"repos":["opengvlab/chartast"],"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/benchmarking-large-language-models-on","slug":"benchmarking-large-language-models-on","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","date":"2024-01-01","arxiv_id":"2401.00690","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/benchmarking-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2401.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00690"}},"official":{"repos":["xt-cyh/codi-eval"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/jatmo-prompt-injection-defense-by-task","slug":"jatmo-prompt-injection-defense-by-task","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","date":"2023-12-29","arxiv_id":"2312.17673","repositories_listed":1,"syntology":{"n":18,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":18,"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) · 8 unverified","sample_list":"/paper/jatmo-prompt-injection-defense-by-task#ran","syntology_url":"https://syntology.ai/paper/2312.17673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17673"}},"official":{"repos":["wagner-group/prompt-injection-defense"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":8,"ran_from_kinds":["official"]}}}],"record_sha256":"a36a836d558798bc831c7bc566245236efeee8728472e31cc8c39697c59e3544","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}