{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/ran/10","list_of":"/task/language-modelling","task":"Language Modelling","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":10,"pages_in_order":25,"rows_per_page":100,"rows":[901,1000],"of":2428,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling/papers/ran/1","prev":"/task/language-modelling/papers/ran/9","next":"/task/language-modelling/papers/ran/11","papers":[{"url":"/paper/bridging-different-language-models-and","slug":"bridging-different-language-models-and","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","date":"2024-03-12","arxiv_id":"2403.07860","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-different-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2403.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07860"}},"official":{"repos":["shihaozhaozsh/lavi-bridge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-text-frozen-large-language-models-in","slug":"beyond-text-frozen-large-language-models-in","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","date":"2024-03-12","arxiv_id":"2403.07874","repositories_listed":1,"syntology":{"n":26,"n_ran":17,"n_constructed":0,"n_ran_checked":6,"n_instrument":11,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":26,"phrase":"17 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; 11 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/beyond-text-frozen-large-language-models-in#ran","syntology_url":"https://syntology.ai/paper/2403.07874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07874"}},"official":{"repos":["zh460045050/v2l-tokenizer"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/drivedreamer-2-llm-enhanced-world-models-for","slug":"drivedreamer-2-llm-enhanced-world-models-for","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","date":"2024-03-11","arxiv_id":"2403.06845","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/drivedreamer-2-llm-enhanced-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.06845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06845"}},"official":null}},{"url":"/paper/mend-meta-demonstration-distillation-for","slug":"mend-meta-demonstration-distillation-for","title":"MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning","date":"2024-03-11","arxiv_id":"2403.06914","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mend-meta-demonstration-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2403.06914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06914"}},"official":{"repos":["bigheiniu/mend"],"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/monitoring-ai-modified-content-at-scale-a","slug":"monitoring-ai-modified-content-at-scale-a","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","date":"2024-03-11","arxiv_id":"2403.07183","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/monitoring-ai-modified-content-at-scale-a#ran","syntology_url":"https://syntology.ai/paper/2403.07183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07183"}},"official":{"repos":["Weixin-Liang/Mapping-the-Increasing-Use-of-LLMs-in-Scientific-Papers"],"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/personalized-lora-for-human-centered-text","slug":"personalized-lora-for-human-centered-text","title":"Personalized LoRA for Human-Centered Text Understanding","date":"2024-03-10","arxiv_id":"2403.06208","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":5,"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/personalized-lora-for-human-centered-text#ran","syntology_url":"https://syntology.ai/paper/2403.06208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06208"}},"official":{"repos":["yoyo-yun/plora"],"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/clinicalmamba-a-generative-clinical-language","slug":"clinicalmamba-a-generative-clinical-language","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","date":"2024-03-09","arxiv_id":"2403.05795","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":1,"n_no_contract":6,"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, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clinicalmamba-a-generative-clinical-language#ran","syntology_url":"https://syntology.ai/paper/2403.05795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05795"}},"official":{"repos":["whaleloops/clinicalmamba"],"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/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ella-equip-diffusion-models-with-llm-for#ran","syntology_url":"https://syntology.ai/paper/2403.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05135"}},"official":null}},{"url":"/paper/tapilot-crossing-benchmarking-and-evolving","slug":"tapilot-crossing-benchmarking-and-evolving","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","date":"2024-03-08","arxiv_id":"2403.05307","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tapilot-crossing-benchmarking-and-evolving#ran","syntology_url":"https://syntology.ai/paper/2403.05307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05307"}},"official":{"repos":["tapilot-crossing/tapilot_code"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","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":1,"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/bias-augmented-consistency-training-reduces#ran","syntology_url":"https://syntology.ai/paper/2403.05518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05518"}},"official":{"repos":["raybears/cot-transparency"],"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/deepseek-vl-towards-real-world-vision","slug":"deepseek-vl-towards-real-world-vision","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","date":"2024-03-08","arxiv_id":"2403.05525","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"11 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepseek-vl-towards-real-world-vision#ran","syntology_url":"https://syntology.ai/paper/2403.05525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05525"}},"official":{"repos":["deepseek-ai/deepseek-vl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-adaptation-of-language-models-with-a","slug":"online-adaptation-of-language-models-with-a","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","date":"2024-03-07","arxiv_id":"2403.04317","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":5,"n_no_contract":3,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 5 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/online-adaptation-of-language-models-with-a#ran","syntology_url":"https://syntology.ai/paper/2403.04317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04317"}},"official":{"repos":["jihoontack/mac"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/embodied-understanding-of-driving-scenarios","slug":"embodied-understanding-of-driving-scenarios","title":"Embodied Understanding of Driving Scenarios","date":"2024-03-07","arxiv_id":"2403.04593","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/embodied-understanding-of-driving-scenarios#ran","syntology_url":"https://syntology.ai/paper/2403.04593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04593"}},"official":{"repos":["opendrivelab/elm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/yi-open-foundation-models-by-01-ai","slug":"yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","arxiv_id":"2403.04652","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/yi-open-foundation-models-by-01-ai#ran","syntology_url":"https://syntology.ai/paper/2403.04652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04652"}},"official":{"repos":["01-ai/yi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/unitable-towards-a-unified-framework-for","slug":"unitable-towards-a-unified-framework-for","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","date":"2024-03-07","arxiv_id":"2403.04822","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unitable-towards-a-unified-framework-for#ran","syntology_url":"https://syntology.ai/paper/2403.04822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04822"}},"official":{"repos":["poloclub/unitable"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-chain-of-thought-driven-reasoning-to","slug":"few-shot-chain-of-thought-driven-reasoning-to","title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","date":"2024-03-07","arxiv_id":"2403.04890","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-chain-of-thought-driven-reasoning-to#ran","syntology_url":"https://syntology.ai/paper/2403.04890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04890"}},"official":{"repos":["coldseal/clinicr"],"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/meacap-memory-augmented-zero-shot-image","slug":"meacap-memory-augmented-zero-shot-image","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","date":"2024-03-06","arxiv_id":"2403.03715","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":1,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/meacap-memory-augmented-zero-shot-image#ran","syntology_url":"https://syntology.ai/paper/2403.03715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03715"}},"official":{"repos":["joeyz0z/meacap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/injecagent-benchmarking-indirect-prompt","slug":"injecagent-benchmarking-indirect-prompt","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","date":"2024-03-05","arxiv_id":"2403.02691","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/injecagent-benchmarking-indirect-prompt#ran","syntology_url":"https://syntology.ai/paper/2403.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02691"}},"official":{"repos":["uiuc-kang-lab/injecagent"],"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/causal-walk-debiasing-multi-hop-fact","slug":"causal-walk-debiasing-multi-hop-fact","title":"Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment","date":"2024-03-05","arxiv_id":"2403.02698","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/causal-walk-debiasing-multi-hop-fact#ran","syntology_url":"https://syntology.ai/paper/2403.02698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02698"}},"official":{"repos":["zcccccz/causalwalk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/android-in-the-zoo-chain-of-action-thought","slug":"android-in-the-zoo-chain-of-action-thought","title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","date":"2024-03-05","arxiv_id":"2403.02713","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/android-in-the-zoo-chain-of-action-thought#ran","syntology_url":"https://syntology.ai/paper/2403.02713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02713"}},"official":{"repos":["imnearth/coat"],"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/an-empirical-study-of-llm-as-a-judge-for-llm","slug":"an-empirical-study-of-llm-as-a-judge-for-llm","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","date":"2024-03-05","arxiv_id":"2403.02839","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-empirical-study-of-llm-as-a-judge-for-llm#ran","syntology_url":"https://syntology.ai/paper/2403.02839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02839"}},"official":{"repos":["huihuichyan/unlimitedjudge"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-instruction-tuned-llms-with-fine","slug":"multi-modal-instruction-tuned-llms-with-fine","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","date":"2024-03-05","arxiv_id":"2403.02969","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-modal-instruction-tuned-llms-with-fine#ran","syntology_url":"https://syntology.ai/paper/2403.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02969"}},"official":{"repos":["jwh97nn/anyref"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-maximize-mutual-information-for-1","slug":"learning-to-maximize-mutual-information-for-1","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","date":"2024-03-05","arxiv_id":"2403.03348","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/learning-to-maximize-mutual-information-for-1#ran","syntology_url":"https://syntology.ai/paper/2403.03348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03348"}},"official":{"repos":["xinchen9/cot_distillation_acl2024"],"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/found-in-the-middle-how-language-models-use","slug":"found-in-the-middle-how-language-models-use","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","date":"2024-03-05","arxiv_id":"2403.04797","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/found-in-the-middle-how-language-models-use#ran","syntology_url":"https://syntology.ai/paper/2403.04797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04797"}},"official":{"repos":["vita-group/ms-poe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-scale-protein-language-model-for","slug":"multi-scale-protein-language-model-for","title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","date":"2024-03-05","arxiv_id":"2403.12995","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-scale-protein-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2403.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12995"}},"official":{"repos":["zhengkangjie/esm-aa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/guardt2i-defending-text-to-image-models-from","slug":"guardt2i-defending-text-to-image-models-from","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","date":"2024-03-03","arxiv_id":"2403.01446","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/guardt2i-defending-text-to-image-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.01446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01446"}},"official":{"repos":["cure-lab/guardt2i"],"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":["listed","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/opengraph-towards-open-graph-foundation","slug":"opengraph-towards-open-graph-foundation","title":"OpenGraph: Towards Open Graph Foundation Models","date":"2024-03-02","arxiv_id":"2403.01121","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/opengraph-towards-open-graph-foundation#ran","syntology_url":"https://syntology.ai/paper/2403.01121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01121"}},"official":{"repos":["hkuds/opengraph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/intactkv-improving-large-language-model","slug":"intactkv-improving-large-language-model","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","date":"2024-03-02","arxiv_id":"2403.01241","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/intactkv-improving-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.01241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01241"}},"official":{"repos":["ruikangliu/IntactKV"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/mitigating-reversal-curse-via-semantic-aware","slug":"mitigating-reversal-curse-via-semantic-aware","title":"Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training","date":"2024-03-01","arxiv_id":"2403.00758","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":6,"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/mitigating-reversal-curse-via-semantic-aware#ran","syntology_url":"https://syntology.ai/paper/2403.00758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00758"}},"official":{"repos":["beeevita/SPT"],"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/merging-text-transformer-models-from","slug":"merging-text-transformer-models-from","title":"Merging Text Transformer Models from Different Initializations","date":"2024-03-01","arxiv_id":"2403.00986","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/merging-text-transformer-models-from#ran","syntology_url":"https://syntology.ai/paper/2403.00986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00986"}},"official":{"repos":["nverma1/merging-text-transformers"],"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/flexllm-a-system-for-co-serving-large","slug":"flexllm-a-system-for-co-serving-large","title":"FlexLLM: A System for Co-Serving Large Language Model Inference and Parameter-Efficient Finetuning","date":"2024-02-29","arxiv_id":"2402.18789","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/flexllm-a-system-for-co-serving-large#ran","syntology_url":"https://syntology.ai/paper/2402.18789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18789"}},"official":{"repos":["flexflow/flexflow"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-and-reducing-catastrophic","slug":"analyzing-and-reducing-catastrophic","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","date":"2024-02-29","arxiv_id":"2402.18865","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/analyzing-and-reducing-catastrophic#ran","syntology_url":"https://syntology.ai/paper/2402.18865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18865"}},"official":{"repos":["which47/llmcl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizable-whole-slide-image","slug":"generalizable-whole-slide-image","title":"Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction","date":"2024-02-29","arxiv_id":"2402.19326","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":5,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generalizable-whole-slide-image#ran","syntology_url":"https://syntology.ai/paper/2402.19326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19326"}},"official":{"repos":["ls1rius/wsi_five"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/griffin-mixing-gated-linear-recurrences-with","slug":"griffin-mixing-gated-linear-recurrences-with","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","date":"2024-02-29","arxiv_id":"2402.19427","repositories_listed":4,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/griffin-mixing-gated-linear-recurrences-with#ran","syntology_url":"https://syntology.ai/paper/2402.19427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19427"}},"official":null}},{"url":"/paper/archer-training-language-model-agents-via","slug":"archer-training-language-model-agents-via","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","date":"2024-02-29","arxiv_id":"2402.19446","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/archer-training-language-model-agents-via#ran","syntology_url":"https://syntology.ai/paper/2402.19446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19446"}},"official":{"repos":["yifeizhou02/archer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rinalmo-general-purpose-rna-language-models","slug":"rinalmo-general-purpose-rna-language-models","title":"RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks","date":"2024-02-29","arxiv_id":"2403.00043","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rinalmo-general-purpose-rna-language-models#ran","syntology_url":"https://syntology.ai/paper/2403.00043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00043"}},"official":{"repos":["lbcb-sci/rinalmo","ml4bio/rna-fm"],"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/resonance-rope-improving-context-length","slug":"resonance-rope-improving-context-length","title":"Resonance RoPE: Improving Context Length Generalization of Large Language Models","date":"2024-02-29","arxiv_id":"2403.00071","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/resonance-rope-improving-context-length#ran","syntology_url":"https://syntology.ai/paper/2403.00071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00071"}},"official":{"repos":["sheryc/resonance_rope"],"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/enhancing-long-term-recommendation-with-bi","slug":"enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","arxiv_id":"2403.00843","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-long-term-recommendation-with-bi#ran","syntology_url":"https://syntology.ai/paper/2403.00843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00843"}},"official":{"repos":["jizhi-zhang/billp"],"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/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"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) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/characterizing-truthfulness-in-large-language","slug":"characterizing-truthfulness-in-large-language","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","date":"2024-02-28","arxiv_id":"2402.18048","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":5,"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/characterizing-truthfulness-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.18048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18048"}},"official":{"repos":["fanyin3639/lid-hallucinationdetection"],"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/unsupervised-information-refinement-training","slug":"unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","arxiv_id":"2402.18150","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-information-refinement-training#ran","syntology_url":"https://syntology.ai/paper/2402.18150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18150"}},"official":{"repos":["xsc1234/info-rag"],"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/cogbench-a-large-language-model-walks-into-a","slug":"cogbench-a-large-language-model-walks-into-a","title":"CogBench: a large language model walks into a psychology lab","date":"2024-02-28","arxiv_id":"2402.18225","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cogbench-a-large-language-model-walks-into-a#ran","syntology_url":"https://syntology.ai/paper/2402.18225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18225"}},"official":{"repos":["juliancodaforno/cogbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-language-models-are-versatile","slug":"diffusion-language-models-are-versatile","title":"Diffusion Language Models Are Versatile Protein Learners","date":"2024-02-28","arxiv_id":"2402.18567","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/diffusion-language-models-are-versatile#ran","syntology_url":"https://syntology.ai/paper/2402.18567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18567"}},"official":{"repos":["bytedance/dplm"],"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/simple-linear-attention-language-models","slug":"simple-linear-attention-language-models","title":"Simple linear attention language models balance the recall-throughput tradeoff","date":"2024-02-28","arxiv_id":"2402.18668","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simple-linear-attention-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.18668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18668"}},"official":{"repos":["hazyresearch/based","hazyresearch/zoology"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounding-language-models-for-visual-entity","slug":"grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","arxiv_id":"2402.18695","repositories_listed":1,"syntology":{"n":26,"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/grounding-language-models-for-visual-entity#ran","syntology_url":"https://syntology.ai/paper/2402.18695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18695"}},"official":{"repos":["mrzilinxiao/autover"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":7,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-is-accurate-generation","slug":"retrieval-is-accurate-generation","title":"Retrieval is Accurate Generation","date":"2024-02-27","arxiv_id":"2402.17532","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-is-accurate-generation#ran","syntology_url":"https://syntology.ai/paper/2402.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17532"}},"official":{"repos":["gmftbygmftby/copyisallyouneed"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","unlocated"]}}},{"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/ravel-evaluating-interpretability-methods-on","slug":"ravel-evaluating-interpretability-methods-on","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","date":"2024-02-27","arxiv_id":"2402.17700","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ravel-evaluating-interpretability-methods-on#ran","syntology_url":"https://syntology.ai/paper/2402.17700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17700"}},"official":{"repos":["explanare/ravel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tower-an-open-multilingual-large-language","slug":"tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","date":"2024-02-27","arxiv_id":"2402.17733","repositories_listed":4,"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":7,"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/tower-an-open-multilingual-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17733"}},"official":{"repos":["deep-spin/tower-eval","epfllm/megatron-llm"],"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/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/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","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/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"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/prediction-powered-ranking-of-large-language","slug":"prediction-powered-ranking-of-large-language","title":"Prediction-Powered Ranking of Large Language Models","date":"2024-02-27","arxiv_id":"2402.17826","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prediction-powered-ranking-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.17826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17826"}},"official":{"repos":["networks-learning/prediction-powered-ranking"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-efficiency-in-sparse-models-with","slug":"enhancing-efficiency-in-sparse-models-with","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","date":"2024-02-27","arxiv_id":"2403.18926","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-efficiency-in-sparse-models-with#ran","syntology_url":"https://syntology.ai/paper/2403.18926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18926"}},"official":{"repos":["ysngki/xmoe"],"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/codes-towards-building-open-source-language","slug":"codes-towards-building-open-source-language","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","date":"2024-02-26","arxiv_id":"2402.16347","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":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) · 4 unverified","sample_list":"/paper/codes-towards-building-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2402.16347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16347"}},"official":{"repos":["ruckbreasoning/codes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-inference-unveiled-survey-and-roofline","slug":"llm-inference-unveiled-survey-and-roofline","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","date":"2024-02-26","arxiv_id":"2402.16363","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-inference-unveiled-survey-and-roofline#ran","syntology_url":"https://syntology.ai/paper/2402.16363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16363"}},"official":{"repos":["hahnyuan/llm-viewer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/defending-llms-against-jailbreaking-attacks","slug":"defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","arxiv_id":"2402.16459","repositories_listed":2,"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":0,"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/defending-llms-against-jailbreaking-attacks#ran","syntology_url":"https://syntology.ai/paper/2402.16459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16459"}},"official":{"repos":["yihanwang617/llm-jailbreaking-defense","yihanwang617/llm-jailbreaking-defense-backtranslation"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"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/repoagent-an-llm-powered-open-source","slug":"repoagent-an-llm-powered-open-source","title":"RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation","date":"2024-02-26","arxiv_id":"2402.16667","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":2,"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/repoagent-an-llm-powered-open-source#ran","syntology_url":"https://syntology.ai/paper/2402.16667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16667"}},"official":{"repos":["openbmb/repoagent"],"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":["found_in_text","official"]}}},{"url":"/paper/a-comprehensive-evaluation-of-quantization","slug":"a-comprehensive-evaluation-of-quantization","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","date":"2024-02-26","arxiv_id":"2402.16775","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-comprehensive-evaluation-of-quantization#ran","syntology_url":"https://syntology.ai/paper/2402.16775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16775"}},"official":{"repos":["cordercorder/quant_eval"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pandora-s-white-box-increased-training-data","slug":"pandora-s-white-box-increased-training-data","title":"Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models","date":"2024-02-26","arxiv_id":"2402.17012","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pandora-s-white-box-increased-training-data#ran","syntology_url":"https://syntology.ai/paper/2402.17012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17012"}},"official":null}},{"url":"/paper/higpt-heterogeneous-graph-language-model","slug":"higpt-heterogeneous-graph-language-model","title":"HiGPT: Heterogeneous Graph Language Model","date":"2024-02-25","arxiv_id":"2402.16024","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/higpt-heterogeneous-graph-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.16024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16024"}},"official":{"repos":["hkuds/higpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/graphwiz-an-instruction-following-language","slug":"graphwiz-an-instruction-following-language","title":"GraphWiz: An Instruction-Following Language Model for Graph Problems","date":"2024-02-25","arxiv_id":"2402.16029","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/graphwiz-an-instruction-following-language#ran","syntology_url":"https://syntology.ai/paper/2402.16029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16029"}},"official":{"repos":["nuochenpku/Graph-Reasoning-LLM"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lstp-language-guided-spatial-temporal-prompt","slug":"lstp-language-guided-spatial-temporal-prompt","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","date":"2024-02-25","arxiv_id":"2402.16050","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lstp-language-guided-spatial-temporal-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16050"}},"official":{"repos":["bigai-nlco/lstp-chat","bigai-nlco/videotgb"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/say-more-with-less-understanding-prompt","slug":"say-more-with-less-understanding-prompt","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","date":"2024-02-25","arxiv_id":"2402.16058","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/say-more-with-less-understanding-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16058"}},"official":{"repos":["openmatch/gist-coco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ldb-a-large-language-model-debugger-via","slug":"ldb-a-large-language-model-debugger-via","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","date":"2024-02-25","arxiv_id":"2402.16906","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ldb-a-large-language-model-debugger-via#ran","syntology_url":"https://syntology.ai/paper/2402.16906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16906"}},"official":{"repos":["floridsleeves/llmdebugger"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/empowering-large-language-model-agents","slug":"empowering-large-language-model-agents","title":"Empowering Large Language Model Agents through Action Learning","date":"2024-02-24","arxiv_id":"2402.15809","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/empowering-large-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2402.15809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15809"}},"official":{"repos":["zhao-ht/learnact"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/item-side-fairness-of-large-language-model","slug":"item-side-fairness-of-large-language-model","title":"Item-side Fairness of Large Language Model-based Recommendation System","date":"2024-02-23","arxiv_id":"2402.15215","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/item-side-fairness-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.15215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15215"}},"official":{"repos":["jiangm-c/ifairlrs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/repetition-improves-language-model-embeddings","slug":"repetition-improves-language-model-embeddings","title":"Repetition Improves Language Model Embeddings","date":"2024-02-23","arxiv_id":"2402.15449","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/repetition-improves-language-model-embeddings#ran","syntology_url":"https://syntology.ai/paper/2402.15449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15449"}},"official":{"repos":["jakespringer/echo-embeddings"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/megascale-scaling-large-language-model","slug":"megascale-scaling-large-language-model","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","date":"2024-02-23","arxiv_id":"2402.15627","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/megascale-scaling-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.15627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15627"}},"official":{"repos":["volcengine/vescale"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-good-and-the-bad-exploring-privacy-issues","slug":"the-good-and-the-bad-exploring-privacy-issues","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","date":"2024-02-23","arxiv_id":"2402.16893","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-good-and-the-bad-exploring-privacy-issues#ran","syntology_url":"https://syntology.ai/paper/2402.16893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16893"}},"official":{"repos":["phycholosogy/rag-privacy"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-retrieval-building-an-information","slug":"self-retrieval-building-an-information","title":"Self-Retrieval: End-to-End Information Retrieval with One Large Language Model","date":"2024-02-23","arxiv_id":"2403.00801","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-retrieval-building-an-information#ran","syntology_url":"https://syntology.ai/paper/2403.00801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00801"}},"official":{"repos":["icip-cas/selfretrieval","tangqiaoyu/selfretrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/subobject-level-image-tokenization","slug":"subobject-level-image-tokenization","title":"Subobject-level Image Tokenization","date":"2024-02-22","arxiv_id":"2402.14327","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/subobject-level-image-tokenization#ran","syntology_url":"https://syntology.ai/paper/2402.14327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14327"}},"official":{"repos":["chendelong1999/subobjects"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-aware-evaluation-for-vision","slug":"uncertainty-aware-evaluation-for-vision","title":"Uncertainty-Aware Evaluation for Vision-Language Models","date":"2024-02-22","arxiv_id":"2402.14418","repositories_listed":1,"syntology":{"n":17,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/uncertainty-aware-evaluation-for-vision#ran","syntology_url":"https://syntology.ai/paper/2402.14418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14418"}},"official":{"repos":["ensec-ai/vlm-uncertainty-bench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/balanced-data-sampling-for-language-model","slug":"balanced-data-sampling-for-language-model","title":"Balanced Data Sampling for Language Model Training with Clustering","date":"2024-02-22","arxiv_id":"2402.14526","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/balanced-data-sampling-for-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.14526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14526"}},"official":{"repos":["choosewhatulike/cluster-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cleaner-pretraining-corpus-curation-with","slug":"cleaner-pretraining-corpus-curation-with","title":"Cleaner Pretraining Corpus Curation with Neural Web Scraping","date":"2024-02-22","arxiv_id":"2402.14652","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleaner-pretraining-corpus-curation-with#ran","syntology_url":"https://syntology.ai/paper/2402.14652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14652"}},"official":{"repos":["openmatch/neuscraper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/q-probe-a-lightweight-approach-to-reward","slug":"q-probe-a-lightweight-approach-to-reward","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","date":"2024-02-22","arxiv_id":"2402.14688","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/q-probe-a-lightweight-approach-to-reward#ran","syntology_url":"https://syntology.ai/paper/2402.14688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14688"}},"official":{"repos":["likenneth/q_probe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/relayattention-for-efficient-large-language","slug":"relayattention-for-efficient-large-language","title":"RelayAttention for Efficient Large Language Model Serving with Long System Prompts","date":"2024-02-22","arxiv_id":"2402.14808","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relayattention-for-efficient-large-language#ran","syntology_url":"https://syntology.ai/paper/2402.14808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14808"}},"official":{"repos":["rayleizhu/vllm-ra"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenization-counts-the-impact-of","slug":"tokenization-counts-the-impact-of","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","date":"2024-02-22","arxiv_id":"2402.14903","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tokenization-counts-the-impact-of#ran","syntology_url":"https://syntology.ai/paper/2402.14903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14903"}},"official":{"repos":["aadityasingh/tokenizationcounts"],"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/watermarking-makes-language-models","slug":"watermarking-makes-language-models","title":"Watermarking Makes Language Models Radioactive","date":"2024-02-22","arxiv_id":"2402.14904","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/watermarking-makes-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.14904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14904"}},"official":{"repos":["facebookresearch/radioactive-watermark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cognitive-visual-language-mapper-advancing","slug":"cognitive-visual-language-mapper-advancing","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","date":"2024-02-21","arxiv_id":"2402.13561","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/cognitive-visual-language-mapper-advancing#ran","syntology_url":"https://syntology.ai/paper/2402.13561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13561"}},"official":{"repos":["hitsz-tmg/cognitive-visual-language-mapper"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/longwanjuan-towards-systematic-measurement","slug":"longwanjuan-towards-systematic-measurement","title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality","date":"2024-02-21","arxiv_id":"2402.13583","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longwanjuan-towards-systematic-measurement#ran","syntology_url":"https://syntology.ai/paper/2402.13583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13583"}},"official":{"repos":["openlmlab/longwanjuan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-distillation-bridges-distribution-gap-in","slug":"self-distillation-bridges-distribution-gap-in","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","date":"2024-02-21","arxiv_id":"2402.13669","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-distillation-bridges-distribution-gap-in#ran","syntology_url":"https://syntology.ai/paper/2402.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13669"}},"official":{"repos":["sail-sg/sdft"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-building-multilingual-language-model","slug":"towards-building-multilingual-language-model","title":"Towards Building Multilingual Language Model for Medicine","date":"2024-02-21","arxiv_id":"2402.13963","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-building-multilingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13963"}},"official":{"repos":["magic-ai4med/mmedlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/analysing-the-impact-of-sequence-composition","slug":"analysing-the-impact-of-sequence-composition","title":"Analysing The Impact of Sequence Composition on Language Model Pre-Training","date":"2024-02-21","arxiv_id":"2402.13991","repositories_listed":1,"syntology":{"n":21,"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analysing-the-impact-of-sequence-composition#ran","syntology_url":"https://syntology.ai/paper/2402.13991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13991"}},"official":{"repos":["yuzhaouoe/pretraining-data-packing"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/distillation-contrastive-decoding-improving","slug":"distillation-contrastive-decoding-improving","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","date":"2024-02-21","arxiv_id":"2402.14874","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/distillation-contrastive-decoding-improving#ran","syntology_url":"https://syntology.ai/paper/2402.14874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14874"}},"official":{"repos":["pphuc25/distil-cd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/arabicmmlu-assessing-massive-multitask","slug":"arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","date":"2024-02-20","arxiv_id":"2402.12840","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/arabicmmlu-assessing-massive-multitask#ran","syntology_url":"https://syntology.ai/paper/2402.12840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12840"}},"official":{"repos":["mbzuai-nlp/arabicmmlu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/backward-lens-projecting-language-model","slug":"backward-lens-projecting-language-model","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","date":"2024-02-20","arxiv_id":"2402.12865","repositories_listed":0,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/backward-lens-projecting-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.12865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12865"}},"official":null}},{"url":"/paper/gumbelsoft-diversified-language-model","slug":"gumbelsoft-diversified-language-model","title":"GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick","date":"2024-02-20","arxiv_id":"2402.12948","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gumbelsoft-diversified-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.12948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12948"}},"official":{"repos":["poruna-byte/gumbelsoft"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trap-targeted-random-adversarial-prompt","slug":"trap-targeted-random-adversarial-prompt","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","date":"2024-02-20","arxiv_id":"2402.12991","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trap-targeted-random-adversarial-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.12991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12991"}},"official":{"repos":["framartin/trap","parameterlab/trap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-the-effects-of-language","slug":"understanding-the-effects-of-language","title":"Understanding the effects of language-specific class imbalance in multilingual fine-tuning","date":"2024-02-20","arxiv_id":"2402.13016","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-the-effects-of-language#ran","syntology_url":"https://syntology.ai/paper/2402.13016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13016"}},"official":{"repos":["idiap/class-imbalance-multilingual-ft"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/heterogeneous-graph-reasoning-for-fact","slug":"heterogeneous-graph-reasoning-for-fact","title":"Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables","date":"2024-02-20","arxiv_id":"2402.13028","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/heterogeneous-graph-reasoning-for-fact#ran","syntology_url":"https://syntology.ai/paper/2402.13028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13028"}},"official":{"repos":["deno-v/heterfc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-guided-molecule-generation-with","slug":"text-guided-molecule-generation-with","title":"Text-Guided Molecule Generation with Diffusion Language Model","date":"2024-02-20","arxiv_id":"2402.13040","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":21,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/text-guided-molecule-generation-with#ran","syntology_url":"https://syntology.ai/paper/2402.13040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13040"}},"official":{"repos":["deno-v/tgm-dlm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/how-do-hyenas-deal-with-human-speech-speech","slug":"how-do-hyenas-deal-with-human-speech-speech","title":"How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena","date":"2024-02-20","arxiv_id":"2402.13208","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-do-hyenas-deal-with-human-speech-speech#ran","syntology_url":"https://syntology.ai/paper/2402.13208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13208"}},"official":{"repos":["hlt-mt/fbk-fairseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/soft-self-consistency-improves-language-model","slug":"soft-self-consistency-improves-language-model","title":"Soft Self-Consistency Improves Language Model Agents","date":"2024-02-20","arxiv_id":"2402.13212","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soft-self-consistency-improves-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.13212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13212"}},"official":{"repos":["hannight/soft_self_consistency"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/softmax-probabilities-mostly-predict-large","slug":"softmax-probabilities-mostly-predict-large","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","date":"2024-02-20","arxiv_id":"2402.13213","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"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; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/softmax-probabilities-mostly-predict-large#ran","syntology_url":"https://syntology.ai/paper/2402.13213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13213"}},"official":{"repos":["bplaut/softmax-probs-predict-llm-correctness","bplaut/llm-calibration-and-correctness-prediction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-touch-vision-and-language-dataset-for","slug":"a-touch-vision-and-language-dataset-for","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","date":"2024-02-20","arxiv_id":"2402.13232","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-touch-vision-and-language-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2402.13232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13232"}},"official":{"repos":["Max-Fu/tvl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/humaneval-on-latest-gpt-models-2024","slug":"humaneval-on-latest-gpt-models-2024","title":"HumanEval on Latest GPT Models -- 2024","date":"2024-02-20","arxiv_id":"2402.14852","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/humaneval-on-latest-gpt-models-2024#ran","syntology_url":"https://syntology.ai/paper/2402.14852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14852"}},"official":{"repos":["daniel442li/gpt-human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generation-meets-verification-accelerating","slug":"generation-meets-verification-accelerating","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","date":"2024-02-19","arxiv_id":"2402.11809","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generation-meets-verification-accelerating#ran","syntology_url":"https://syntology.ai/paper/2402.11809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11809"}},"official":{"repos":["cteant/space","hiyouga/llama-factory"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"9fdd58f861168ffa1dddd9bb168303118c3e79e56f0839aafbea4c5cadbd0e20","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}