{"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/28","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":28,"pages_in_order":177,"rows_per_page":100,"rows":[2701,2800],"of":17610,"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","prev":"/task/language-modelling/papers/27","next":"/task/language-modelling/papers/29","papers":[{"url":"/paper/fine-tuning-with-divergent-chains-of-thought","slug":"fine-tuning-with-divergent-chains-of-thought","title":"Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models","date":"2024-07-03","arxiv_id":"2407.03181","repositories_listed":1,"syntology":null},{"url":"/paper/internlm-xcomposer-2-5-a-versatile-large","slug":"internlm-xcomposer-2-5-a-versatile-large","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","date":"2024-07-03","arxiv_id":"2407.03320","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/internlm-xcomposer-2-5-a-versatile-large#ran","syntology_url":"https://syntology.ai/paper/2407.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03320"}},"official":{"repos":["internlm/internlm-xcomposer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/planetarium-a-rigorous-benchmark-for","slug":"planetarium-a-rigorous-benchmark-for","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","date":"2024-07-03","arxiv_id":"2407.03321","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/planetarium-a-rigorous-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.03321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03321"}},"official":{"repos":["batsresearch/planetarium"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"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/gptcast-a-weather-language-model-for","slug":"gptcast-a-weather-language-model-for","title":"GPTCast: a weather language model for precipitation nowcasting","date":"2024-07-02","arxiv_id":"2407.02089","repositories_listed":1,"syntology":null},{"url":"/paper/helpful-assistant-or-fruitful-facilitator","slug":"helpful-assistant-or-fruitful-facilitator","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","date":"2024-07-02","arxiv_id":"2407.02099","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/helpful-assistant-or-fruitful-facilitator#ran","syntology_url":"https://syntology.ai/paper/2407.02099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02099"}},"official":{"repos":["peluz/persona-behavior"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/is-your-large-language-model-knowledgeable-or","slug":"is-your-large-language-model-knowledgeable-or","title":"Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?","date":"2024-07-02","arxiv_id":"2407.01992","repositories_listed":1,"syntology":null},{"url":"/paper/neurocache-efficient-vector-retrieval-for","slug":"neurocache-efficient-vector-retrieval-for","title":"Neurocache: Efficient Vector Retrieval for Long-range Language Modeling","date":"2024-07-02","arxiv_id":"2407.02486","repositories_listed":1,"syntology":null},{"url":"/paper/tokenpacker-efficient-visual-projector-for","slug":"tokenpacker-efficient-visual-projector-for","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","date":"2024-07-02","arxiv_id":"2407.02392","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/tokenpacker-efficient-visual-projector-for#ran","syntology_url":"https://syntology.ai/paper/2407.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02392"}},"official":{"repos":["circleradon/tokenpacker"],"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/adapting-multilingual-llms-to-low-resource","slug":"adapting-multilingual-llms-to-low-resource","title":"Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters","date":"2024-07-01","arxiv_id":"2407.01406","repositories_listed":1,"syntology":null},{"url":"/paper/autoflow-automated-workflow-generation-for","slug":"autoflow-automated-workflow-generation-for","title":"AutoFlow: Automated Workflow Generation for Large Language Model Agents","date":"2024-07-01","arxiv_id":"2407.12821","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autoflow-automated-workflow-generation-for#ran","syntology_url":"https://syntology.ai/paper/2407.12821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12821"}},"official":{"repos":["agiresearch/autoflow"],"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/crab-cross-environment-agent-benchmark-for","slug":"crab-cross-environment-agent-benchmark-for","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","date":"2024-07-01","arxiv_id":"2407.01511","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crab-cross-environment-agent-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.01511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01511"}},"official":{"repos":["camel-ai/crab"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/empathic-grounding-explorations-using","slug":"empathic-grounding-explorations-using","title":"Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational Agents","date":"2024-07-01","arxiv_id":"2407.01824","repositories_listed":1,"syntology":null},{"url":"/paper/ibsen-director-actor-agent-collaboration-for","slug":"ibsen-director-actor-agent-collaboration-for","title":"IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation","date":"2024-07-01","arxiv_id":"2407.01093","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ibsen-director-actor-agent-collaboration-for#ran","syntology_url":"https://syntology.ai/paper/2407.01093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01093"}},"official":{"repos":["OpenDFM/ibsen"],"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/large-language-models-are-involuntary-truth","slug":"large-language-models-are-involuntary-truth","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","date":"2024-07-01","arxiv_id":"2407.00869","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/large-language-models-are-involuntary-truth#ran","syntology_url":"https://syntology.ai/paper/2407.00869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00869"}},"official":{"repos":["Yue-LLM-Pit/FFA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-explore-and-select-for-coverage","slug":"learning-to-explore-and-select-for-coverage","title":"Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation","date":"2024-07-01","arxiv_id":"2407.01158","repositories_listed":1,"syntology":null},{"url":"/paper/meerkat-audio-visual-large-language-model-for","slug":"meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","arxiv_id":"2407.01851","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/meerkat-audio-visual-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2407.01851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01851"}},"official":{"repos":["schowdhury671/meerkat"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/regmix-data-mixture-as-regression-for","slug":"regmix-data-mixture-as-regression-for","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","date":"2024-07-01","arxiv_id":"2407.01492","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/regmix-data-mixture-as-regression-for#ran","syntology_url":"https://syntology.ai/paper/2407.01492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01492"}},"official":{"repos":["sail-sg/regmix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-random-walks-for-learning-on","slug":"revisiting-random-walks-for-learning-on","title":"Revisiting Random Walks for Learning on Graphs","date":"2024-07-01","arxiv_id":"2407.01214","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-random-walks-for-learning-on#ran","syntology_url":"https://syntology.ai/paper/2407.01214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01214"}},"official":{"repos":["jw9730/random-walk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sinkt-a-structure-aware-inductive-knowledge","slug":"sinkt-a-structure-aware-inductive-knowledge","title":"SINKT: A Structure-Aware Inductive Knowledge Tracing Model with Large Language Model","date":"2024-07-01","arxiv_id":"2407.01245","repositories_listed":1,"syntology":null},{"url":"/paper/tree-search-for-language-model-agents","slug":"tree-search-for-language-model-agents","title":"Tree Search for Language Model Agents","date":"2024-07-01","arxiv_id":"2407.01476","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tree-search-for-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2407.01476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01476"}},"official":null}},{"url":"/paper/teola-towards-end-to-end-optimization-of-llm","slug":"teola-towards-end-to-end-optimization-of-llm","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","date":"2024-06-29","arxiv_id":"2407.00326","repositories_listed":1,"syntology":null},{"url":"/paper/the-factuality-tax-of-diversity-intervened","slug":"the-factuality-tax-of-diversity-intervened","title":"The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention","date":"2024-06-29","arxiv_id":"2407.00377","repositories_listed":1,"syntology":null},{"url":"/paper/evf-sam-early-vision-language-fusion-for-text","slug":"evf-sam-early-vision-language-fusion-for-text","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","date":"2024-06-28","arxiv_id":"2406.20076","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":2,"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/evf-sam-early-vision-language-fusion-for-text#ran","syntology_url":"https://syntology.ai/paper/2406.20076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20076"}},"official":{"repos":["hustvl/evf-sam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/into-the-unknown-generating-geospatial","slug":"into-the-unknown-generating-geospatial","title":"Into the Unknown: Generating Geospatial Descriptions for New Environments","date":"2024-06-28","arxiv_id":"2406.19967","repositories_listed":1,"syntology":null},{"url":"/paper/molecular-facts-desiderata-for","slug":"molecular-facts-desiderata-for","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","date":"2024-06-28","arxiv_id":"2406.20079","repositories_listed":1,"syntology":null},{"url":"/paper/solving-token-gradient-conflict-in-mixture-of","slug":"solving-token-gradient-conflict-in-mixture-of","title":"Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model","date":"2024-06-28","arxiv_id":"2406.19905","repositories_listed":1,"syntology":null},{"url":"/paper/yulan-an-open-source-large-language-model","slug":"yulan-an-open-source-large-language-model","title":"YuLan: An Open-source Large Language Model","date":"2024-06-28","arxiv_id":"2406.19853","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/yulan-an-open-source-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.19853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19853"}},"official":{"repos":["ruc-gsai/yulan-chat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decoding-time-language-model-alignment-with","slug":"decoding-time-language-model-alignment-with","title":"Decoding-Time Language Model Alignment with Multiple Objectives","date":"2024-06-27","arxiv_id":"2406.18853","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/decoding-time-language-model-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2406.18853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18853"}},"official":{"repos":["srzer/mod"],"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/efficacy-of-language-model-self-play-in-non","slug":"efficacy-of-language-model-self-play-in-non","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games","date":"2024-06-27","arxiv_id":"2406.18872","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficacy-of-language-model-self-play-in-non#ran","syntology_url":"https://syntology.ai/paper/2406.18872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18872"}},"official":{"repos":["nickatomlin/lm-selfplay"],"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/length-optimization-in-conformal-prediction","slug":"length-optimization-in-conformal-prediction","title":"Length Optimization in Conformal Prediction","date":"2024-06-27","arxiv_id":"2406.18814","repositories_listed":1,"syntology":null},{"url":"/paper/robouniview-visual-language-model-with","slug":"robouniview-visual-language-model-with","title":"RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation","date":"2024-06-27","arxiv_id":"2406.18977","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/robouniview-visual-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2406.18977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18977"}},"official":{"repos":["liufanfanlff/robouniview"],"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/a-refer-and-ground-multimodal-large-language","slug":"a-refer-and-ground-multimodal-large-language","title":"A Refer-and-Ground Multimodal Large Language Model for Biomedicine","date":"2024-06-26","arxiv_id":"2406.18146","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-refer-and-ground-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.18146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18146"}},"official":{"repos":["shawnhuang497/bird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/badge-badminton-report-generation-and","slug":"badge-badminton-report-generation-and","title":"BADGE: BADminton report Generation and Evaluation with LLM","date":"2024-06-26","arxiv_id":"2406.18116","repositories_listed":1,"syntology":null},{"url":"/paper/cascading-large-language-models-for-salient","slug":"cascading-large-language-models-for-salient","title":"Cascading Large Language Models for Salient Event Graph Generation","date":"2024-06-26","arxiv_id":"2406.18449","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graph-enhanced-retrieval-augmented","slug":"knowledge-graph-enhanced-retrieval-augmented","title":"Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis","date":"2024-06-26","arxiv_id":"2406.18114","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-pre-trained-models-for-ff-to-ffpe","slug":"leveraging-pre-trained-models-for-ff-to-ffpe","title":"Leveraging Pre-trained Models for FF-to-FFPE Histopathological Image Translation","date":"2024-06-26","arxiv_id":"2406.18054","repositories_listed":1,"syntology":null},{"url":"/paper/s3-a-simple-strong-sample-effective","slug":"s3-a-simple-strong-sample-effective","title":"S3: A Simple Strong Sample-effective Multimodal Dialog System","date":"2024-06-26","arxiv_id":"2406.18305","repositories_listed":1,"syntology":null},{"url":"/paper/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/themis-towards-flexible-and-interpretable-nlg#ran","syntology_url":"https://syntology.ai/paper/2406.18365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18365"}},"official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-we-trust-the-performance-evaluation-of","slug":"can-we-trust-the-performance-evaluation-of","title":"Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?","date":"2024-06-25","arxiv_id":"2406.17274","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/can-we-trust-the-performance-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2406.17274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17274"}},"official":{"repos":["he159ok/benchmark-of-uncertainty-estimation-methods-in-text-summarization"],"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/cogmg-collaborative-augmentation-between","slug":"cogmg-collaborative-augmentation-between","title":"CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph","date":"2024-06-25","arxiv_id":"2406.17231","repositories_listed":1,"syntology":null},{"url":"/paper/cosafe-evaluating-large-language-model-safety","slug":"cosafe-evaluating-large-language-model-safety","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","date":"2024-06-25","arxiv_id":"2406.17626","repositories_listed":1,"syntology":null},{"url":"/paper/ctbench-a-comprehensive-benchmark-for","slug":"ctbench-a-comprehensive-benchmark-for","title":"CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design","date":"2024-06-25","arxiv_id":"2406.17888","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-tool-retrieval-with-iterative","slug":"enhancing-tool-retrieval-with-iterative","title":"Enhancing Tool Retrieval with Iterative Feedback from Large Language Models","date":"2024-06-25","arxiv_id":"2406.17465","repositories_listed":1,"syntology":null},{"url":"/paper/from-distributional-to-overton-pluralism","slug":"from-distributional-to-overton-pluralism","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","date":"2024-06-25","arxiv_id":"2406.17692","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/from-distributional-to-overton-pluralism#ran","syntology_url":"https://syntology.ai/paper/2406.17692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17692"}},"official":{"repos":["thomlake/investigating-alignment"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grass-compute-efficient-low-memory-llm","slug":"grass-compute-efficient-low-memory-llm","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","date":"2024-06-25","arxiv_id":"2406.17660","repositories_listed":1,"syntology":null},{"url":"/paper/make-some-noise-unlocking-language-model","slug":"make-some-noise-unlocking-language-model","title":"Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training","date":"2024-06-25","arxiv_id":"2406.17404","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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/make-some-noise-unlocking-language-model#ran","syntology_url":"https://syntology.ai/paper/2406.17404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17404"}},"official":{"repos":["wyxstriker/MakeSomeNoiseInference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-property-steering-of-large-language","slug":"multi-property-steering-of-large-language","title":"Multi-property Steering of Large Language Models with Dynamic Activation Composition","date":"2024-06-25","arxiv_id":"2406.17563","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-property-steering-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.17563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17563"}},"official":{"repos":["danielsc4/dynamic-activation-composition"],"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/native-design-bias-studying-the-impact-of","slug":"native-design-bias-studying-the-impact-of","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","date":"2024-06-25","arxiv_id":"2406.17385","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"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) · 7 unverified","sample_list":"/paper/native-design-bias-studying-the-impact-of#ran","syntology_url":"https://syntology.ai/paper/2406.17385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17385"}},"official":{"repos":["manon-reusens/native_en_bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-style-in-context-learning-for-few","slug":"retrieval-style-in-context-learning-for-few","title":"Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification","date":"2024-06-25","arxiv_id":"2406.17534","repositories_listed":1,"syntology":null},{"url":"/paper/the-alchemist-automated-labeling-500x-cheaper","slug":"the-alchemist-automated-labeling-500x-cheaper","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","date":"2024-06-25","arxiv_id":"2407.11004","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-alchemist-automated-labeling-500x-cheaper#ran","syntology_url":"https://syntology.ai/paper/2407.11004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11004"}},"official":{"repos":["sprocketlab/alchemist"],"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/the-fineweb-datasets-decanting-the-web-for","slug":"the-fineweb-datasets-decanting-the-web-for","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","date":"2024-06-25","arxiv_id":"2406.17557","repositories_listed":1,"syntology":null},{"url":"/paper/trawl-tensor-reduced-and-approximated-weights","slug":"trawl-tensor-reduced-and-approximated-weights","title":"TRAWL: Tensor Reduced and Approximated Weights for Large Language Models","date":"2024-06-25","arxiv_id":"2406.17261","repositories_listed":1,"syntology":null},{"url":"/paper/varbench-robust-language-model-benchmarking","slug":"varbench-robust-language-model-benchmarking","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","date":"2024-06-25","arxiv_id":"2406.17681","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/varbench-robust-language-model-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.17681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17681"}},"official":{"repos":["qbetterk/VarBench"],"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/variable-layer-wise-quantization-a-simple-and","slug":"variable-layer-wise-quantization-a-simple-and","title":"Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels","date":"2024-06-25","arxiv_id":"2406.17415","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-language-model-for-predicting-t-cell","slug":"a-large-language-model-for-predicting-t-cell","title":"tcrLM: a lightweight protein language model for predicting T cell receptor and epitope binding specificity","date":"2024-06-24","arxiv_id":"2406.16995","repositories_listed":1,"syntology":null},{"url":"/paper/c-llm-learn-to-check-chinese-spelling-errors","slug":"c-llm-learn-to-check-chinese-spelling-errors","title":"C-LLM: Learn to Check Chinese Spelling Errors Character by Character","date":"2024-06-24","arxiv_id":"2406.16536","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/c-llm-learn-to-check-chinese-spelling-errors#ran","syntology_url":"https://syntology.ai/paper/2406.16536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16536"}},"official":{"repos":["ktlktl/c-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dalpsr-leverage-degradation-aligned-language","slug":"dalpsr-leverage-degradation-aligned-language","title":"DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution","date":"2024-06-24","arxiv_id":"2406.16477","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-language-models-in-the-medical","slug":"evaluation-of-language-models-in-the-medical","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","date":"2024-06-24","arxiv_id":"2406.16611","repositories_listed":1,"syntology":null},{"url":"/paper/finding-transformer-circuits-with-edge","slug":"finding-transformer-circuits-with-edge","title":"Finding Transformer Circuits with Edge Pruning","date":"2024-06-24","arxiv_id":"2406.16778","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finding-transformer-circuits-with-edge#ran","syntology_url":"https://syntology.ai/paper/2406.16778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16778"}},"official":{"repos":["princeton-nlp/edge-pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/otce-hybrid-ssm-and-attention-with-cross","slug":"otce-hybrid-ssm-and-attention-with-cross","title":"OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser","date":"2024-06-24","arxiv_id":"2406.16495","repositories_listed":1,"syntology":null},{"url":"/paper/res-q-evaluating-code-editing-large-language","slug":"res-q-evaluating-code-editing-large-language","title":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","date":"2024-06-24","arxiv_id":"2406.16801","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/res-q-evaluating-code-editing-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16801"}},"official":{"repos":["qurrent-ai/res-q"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/first-heuristic-then-rational-dynamic-use-of","slug":"first-heuristic-then-rational-dynamic-use-of","title":"First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning","date":"2024-06-23","arxiv_id":"2406.16078","repositories_listed":1,"syntology":null},{"url":"/paper/edge-llm-enabling-efficient-large-language","slug":"edge-llm-enabling-efficient-large-language","title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","date":"2024-06-22","arxiv_id":"2406.15758","repositories_listed":1,"syntology":null},{"url":"/paper/tacolm-gated-attention-equipped-codec","slug":"tacolm-gated-attention-equipped-codec","title":"TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers","date":"2024-06-22","arxiv_id":"2406.15752","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-llms-to-abstain-across-languages-via","slug":"teaching-llms-to-abstain-across-languages-via","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","date":"2024-06-22","arxiv_id":"2406.15948","repositories_listed":1,"syntology":null},{"url":"/paper/brain-like-language-processing-via-a-shallow","slug":"brain-like-language-processing-via-a-shallow","title":"Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network","date":"2024-06-21","arxiv_id":"2406.15109","repositories_listed":1,"syntology":null},{"url":"/paper/first-faster-improved-listwise-reranking-with","slug":"first-faster-improved-listwise-reranking-with","title":"FIRST: Faster Improved Listwise Reranking with Single Token Decoding","date":"2024-06-21","arxiv_id":"2406.15657","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":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/first-faster-improved-listwise-reranking-with#ran","syntology_url":"https://syntology.ai/paper/2406.15657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15657"}},"official":{"repos":["gangiswag/llm-reranker"],"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/internlm-law-an-open-source-chinese-legal","slug":"internlm-law-an-open-source-chinese-legal","title":"InternLM-Law: An Open Source Chinese Legal Large Language Model","date":"2024-06-21","arxiv_id":"2406.14887","repositories_listed":1,"syntology":null},{"url":"/paper/moa-mixture-of-sparse-attention-for-automatic","slug":"moa-mixture-of-sparse-attention-for-automatic","title":"MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression","date":"2024-06-21","arxiv_id":"2406.14909","repositories_listed":1,"syntology":{"n":22,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moa-mixture-of-sparse-attention-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2406.14909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14909"}},"official":{"repos":["thu-nics/moa"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/safely-learning-with-private-data-a-federated","slug":"safely-learning-with-private-data-a-federated","title":"Safely Learning with Private Data: A Federated Learning Framework for Large Language Model","date":"2024-06-21","arxiv_id":"2406.14898","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safely-learning-with-private-data-a-federated#ran","syntology_url":"https://syntology.ai/paper/2406.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14898"}},"official":{"repos":["TAP-LLM/SplitFedLLM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/tinystyler-efficient-few-shot-text-style","slug":"tinystyler-efficient-few-shot-text-style","title":"TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings","date":"2024-06-21","arxiv_id":"2406.15586","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-large-language-model-enhanced","slug":"asynchronous-large-language-model-enhanced","title":"Asynchronous Large Language Model Enhanced Planner for Autonomous Driving","date":"2024-06-20","arxiv_id":"2406.14556","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/asynchronous-large-language-model-enhanced#ran","syntology_url":"https://syntology.ai/paper/2406.14556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14556"}},"official":{"repos":["memberre/asyncdriver"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/citybench-evaluating-the-capabilities-of","slug":"citybench-evaluating-the-capabilities-of","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","date":"2024-06-20","arxiv_id":"2406.13945","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"17 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/citybench-evaluating-the-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2406.13945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13945"}},"official":{"repos":["tsinghua-fib-lab/citybench"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/inference-time-decontamination-reusing-leaked","slug":"inference-time-decontamination-reusing-leaked","title":"Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation","date":"2024-06-20","arxiv_id":"2406.13990","repositories_listed":1,"syntology":null},{"url":"/paper/information-guided-regularization-for-fine","slug":"information-guided-regularization-for-fine","title":"Information Guided Regularization for Fine-tuning Language Models","date":"2024-06-20","arxiv_id":"2406.14005","repositories_listed":1,"syntology":null},{"url":"/paper/livemind-low-latency-large-language-models","slug":"livemind-low-latency-large-language-models","title":"LiveMind: Low-latency Large Language Models with Simultaneous Inference","date":"2024-06-20","arxiv_id":"2406.14319","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/livemind-low-latency-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.14319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14319"}},"official":{"repos":["chuangtaochen-tum/livemind"],"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/llm-a-large-language-model-enhanced","slug":"llm-a-large-language-model-enhanced","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","date":"2024-06-20","arxiv_id":"2407.02511","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-a-large-language-model-enhanced#ran","syntology_url":"https://syntology.ai/paper/2407.02511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02511"}},"official":{"repos":["SilinMeng0510/llm-astar"],"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/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prism-a-framework-for-decoupling-and#ran","syntology_url":"https://syntology.ai/paper/2406.14544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14544"}},"official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/realhf-optimized-rlhf-training-for-large","slug":"realhf-optimized-rlhf-training-for-large","title":"ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation","date":"2024-06-20","arxiv_id":"2406.14088","repositories_listed":1,"syntology":null},{"url":"/paper/revealing-vision-language-integration-in-the","slug":"revealing-vision-language-integration-in-the","title":"Revealing Vision-Language Integration in the Brain with Multimodal Networks","date":"2024-06-20","arxiv_id":"2406.14481","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revealing-vision-language-integration-in-the#ran","syntology_url":"https://syntology.ai/paper/2406.14481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14481"}},"official":{"repos":["vsubramaniam851/brain-multimodal"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sorry-bench-systematically-evaluating-large","slug":"sorry-bench-systematically-evaluating-large","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors","date":"2024-06-20","arxiv_id":"2406.14598","repositories_listed":1,"syntology":null},{"url":"/paper/vlbiasbench-a-comprehensive-benchmark-for","slug":"vlbiasbench-a-comprehensive-benchmark-for","title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","date":"2024-06-20","arxiv_id":"2406.14194","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/vlbiasbench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.14194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14194"}},"official":{"repos":["xiangkui-cao/vlbiasbench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/appl-a-prompt-programming-language-for","slug":"appl-a-prompt-programming-language-for","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","date":"2024-06-19","arxiv_id":"2406.13161","repositories_listed":1,"syntology":null},{"url":"/paper/bild-bi-directional-logits-difference-loss","slug":"bild-bi-directional-logits-difference-loss","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","date":"2024-06-19","arxiv_id":"2406.13555","repositories_listed":1,"syntology":null},{"url":"/paper/elliptical-attention","slug":"elliptical-attention","title":"Elliptical Attention","date":"2024-06-19","arxiv_id":"2406.13770","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/elliptical-attention#ran","syntology_url":"https://syntology.ai/paper/2406.13770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13770"}},"official":{"repos":["stefvk/elliptical-attention"],"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/enhancing-language-model-factuality-via","slug":"enhancing-language-model-factuality-via","title":"Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding","date":"2024-06-19","arxiv_id":"2406.13230","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-commonsense-in-language","slug":"improving-visual-commonsense-in-language","title":"Improving Visual Commonsense in Language Models via Multiple Image Generation","date":"2024-06-19","arxiv_id":"2406.13621","repositories_listed":1,"syntology":null},{"url":"/paper/on-ai-inspired-ui-design","slug":"on-ai-inspired-ui-design","title":"On AI-Inspired UI-Design","date":"2024-06-19","arxiv_id":"2406.13631","repositories_listed":1,"syntology":null},{"url":"/paper/patholm-identifying-pathogenicity-from-the","slug":"patholm-identifying-pathogenicity-from-the","title":"PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model","date":"2024-06-19","arxiv_id":"2406.13133","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/patholm-identifying-pathogenicity-from-the#ran","syntology_url":"https://syntology.ai/paper/2406.13133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13133"}},"official":{"repos":["Sajib-006/Patho-LM"],"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/unveiling-the-hidden-structure-of-self","slug":"unveiling-the-hidden-structure-of-self","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","date":"2024-06-19","arxiv_id":"2406.13762","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":3,"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/unveiling-the-hidden-structure-of-self#ran","syntology_url":"https://syntology.ai/paper/2406.13762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13762"}},"official":{"repos":["rachtsy/kpca_code"],"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/visualrwkv-exploring-recurrent-neural","slug":"visualrwkv-exploring-recurrent-neural","title":"VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models","date":"2024-06-19","arxiv_id":"2406.13362","repositories_listed":1,"syntology":null},{"url":"/paper/2406-15487","slug":"2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","arxiv_id":"2406.15487","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2406-15487#ran","syntology_url":"https://syntology.ai/paper/2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}},"official":null}},{"url":"/paper/agentreview-exploring-peer-review-dynamics","slug":"agentreview-exploring-peer-review-dynamics","title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","date":"2024-06-18","arxiv_id":"2406.12708","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agentreview-exploring-peer-review-dynamics#ran","syntology_url":"https://syntology.ai/paper/2406.12708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12708"}},"official":{"repos":["ahren09/agentreview"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-benchmarking-of-large-multimodal","slug":"automatic-benchmarking-of-large-multimodal","title":"Automatic benchmarking of large multimodal models via iterative experiment programming","date":"2024-06-18","arxiv_id":"2406.12321","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-ceiling-of-the-llm-community-by","slug":"breaking-the-ceiling-of-the-llm-community-by","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","date":"2024-06-18","arxiv_id":"2406.12585","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":1,"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/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}},"official":{"repos":["yaoching0/gac"],"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/detectbench-can-large-language-model-detect","slug":"detectbench-can-large-language-model-detect","title":"DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?","date":"2024-06-18","arxiv_id":"2406.12641","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-errors-through-ensembling-prompts","slug":"detecting-errors-through-ensembling-prompts","title":"Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors","date":"2024-06-18","arxiv_id":"2406.13009","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-and-long-tailed-generalization-for","slug":"efficient-and-long-tailed-generalization-for","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","date":"2024-06-18","arxiv_id":"2406.12638","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-and-long-tailed-generalization-for#ran","syntology_url":"https://syntology.ai/paper/2406.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12638"}},"official":{"repos":["shijxcs/candle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/holmes-vad-towards-unbiased-and-explainable","slug":"holmes-vad-towards-unbiased-and-explainable","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","date":"2024-06-18","arxiv_id":"2406.12235","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":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/holmes-vad-towards-unbiased-and-explainable#ran","syntology_url":"https://syntology.ai/paper/2406.12235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12235"}},"official":{"repos":["pipixin321/holmesvad"],"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"]}}}],"record_sha256":"925920711bf01968ef6af12940551ed222d1979316927f9d788d42760d44e5cd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}