{"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/hallucination","name":"Hallucination","slug":"hallucination","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1816,"papers_with_code":752,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mmneedle","name":"MMNeedle","full_name":"Multimodal Needle in a Haystack","num_papers_in_archive":12}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":19,"rows_per_page":100,"shown":100,"of":1816,"of_with_code":752,"tagged_in_all":1816,"counts":{"archive_papers_tagged":1816,"with_a_code_link":752,"where_syntology_ran_a_sample":276,"not_listed_spam_title":0,"listed":1816,"listed_where_code_ran":276,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":224,"every_run_a_failure_of_syntologys_instrument":52,"listed_with_a_run_with_no_instrument_failure":224,"listed_every_run_a_failure_of_syntologys_instrument":52,"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"},"items":[{"url":"/paper/pulse-self-supervised-photo-upsampling-via","slug":"pulse-self-supervised-photo-upsampling-via","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","date":"2020-03-08","arxiv_id":"2003.03808","repositories_listed":16,"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/pulse-self-supervised-photo-upsampling-via#ran","syntology_url":"https://syntology.ai/paper/2003.03808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03808"}},"official":{"repos":["adamian98/pulse"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/hallusionbench-you-see-what-you-think-or-you","slug":"hallusionbench-you-see-what-you-think-or-you","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","date":"2023-10-23","arxiv_id":"2310.14566","repositories_listed":9,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hallusionbench-you-see-what-you-think-or-you#ran","syntology_url":"https://syntology.ai/paper/2310.14566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14566"}},"official":{"repos":["tianyi-lab/hallusionbench"],"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":["listed","official"]}}},{"url":"/paper/react-synergizing-reasoning-and-acting-in","slug":"react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","arxiv_id":"2210.03629","repositories_listed":9,"syntology":{"n":34,"n_ran":15,"n_constructed":9,"n_ran_checked":10,"n_instrument":5,"n_unverified":19,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"15 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/react-synergizing-reasoning-and-acting-in#ran","syntology_url":"https://syntology.ai/paper/2210.03629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03629"}},"official":{"repos":["ysymyth/ReAct"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mitigating-object-hallucinations-in-large","slug":"mitigating-object-hallucinations-in-large","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","date":"2023-11-28","arxiv_id":"2311.16922","repositories_listed":7,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"10 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; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-object-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2311.16922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16922"}},"official":{"repos":["bradyfu/awesome-multimodal-large-language-models","damo-nlp-sg/vcd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/evaluating-object-hallucination-in-large","slug":"evaluating-object-hallucination-in-large","title":"Evaluating Object Hallucination in Large Vision-Language Models","date":"2023-05-17","arxiv_id":"2305.10355","repositories_listed":6,"syntology":{"n":12,"n_ran":11,"n_constructed":2,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evaluating-object-hallucination-in-large#ran","syntology_url":"https://syntology.ai/paper/2305.10355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10355"}},"official":{"repos":["rucaibox/pope"],"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":["listed","official"]}}},{"url":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","slug":"rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","arxiv_id":"2405.17220","repositories_listed":5,"syntology":{"n":22,"n_ran":17,"n_constructed":0,"n_ran_checked":7,"n_instrument":10,"n_unverified":5,"n_honours":2,"n_violates":3,"n_no_contract":2,"n_pointer_only":17,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rlaif-v-aligning-mllms-through-open-source-ai#ran","syntology_url":"https://syntology.ai/paper/2405.17220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17220"}},"official":{"repos":["openbmb/omnilmm","rlhf-v/rlaif-v"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/retrieval-augmented-generation-for-large","slug":"retrieval-augmented-generation-for-large","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","date":"2023-12-18","arxiv_id":"2312.10997","repositories_listed":4,"syntology":null},{"url":"/paper/rlhf-v-towards-trustworthy-mllms-via-behavior","slug":"rlhf-v-towards-trustworthy-mllms-via-behavior","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","date":"2023-12-01","arxiv_id":"2312.00849","repositories_listed":4,"syntology":null},{"url":"/paper/aligning-large-multi-modal-model-with-robust","slug":"aligning-large-multi-modal-model-with-robust","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","date":"2023-06-26","arxiv_id":"2306.14565","repositories_listed":4,"syntology":null},{"url":"/paper/projected-distribution-loss-for-image","slug":"projected-distribution-loss-for-image","title":"Projected Distribution Loss for Image Enhancement","date":"2020-12-16","arxiv_id":"2012.09289","repositories_listed":4,"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/projected-distribution-loss-for-image#ran","syntology_url":"https://syntology.ai/paper/2012.09289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09289"}},"official":null}},{"url":"/paper/pushing-the-limits-of-low-resource","slug":"pushing-the-limits-of-low-resource","title":"Pushing the Limits of Low-Resource Morphological Inflection","date":"2019-08-16","arxiv_id":"1908.05838","repositories_listed":4,"syntology":null},{"url":"/paper/im2flow-motion-hallucination-from-static","slug":"im2flow-motion-hallucination-from-static","title":"Im2Flow: Motion Hallucination from Static Images for Action Recognition","date":"2017-12-12","arxiv_id":"1712.04109","repositories_listed":4,"syntology":null},{"url":"/paper/evolutionary-thoughts-integration-of-large","slug":"evolutionary-thoughts-integration-of-large","title":"Evolutionary thoughts: integration of large language models and evolutionary algorithms","date":"2025-05-09","arxiv_id":"2505.05756","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evolutionary-thoughts-integration-of-large#ran","syntology_url":"https://syntology.ai/paper/2505.05756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05756"}},"official":{"repos":["ajjimeno/fast-evolutionary-evaluation","ajjimeno/list-data","ajjimeno/llm-gp"],"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/benchmark-evaluations-applications-and","slug":"benchmark-evaluations-applications-and","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","date":"2025-01-04","arxiv_id":"2501.02189","repositories_listed":3,"syntology":null},{"url":"/paper/embodied-agent-interface-benchmarking-llms","slug":"embodied-agent-interface-benchmarking-llms","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","date":"2024-10-09","arxiv_id":"2410.07166","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/embodied-agent-interface-benchmarking-llms#ran","syntology_url":"https://syntology.ai/paper/2410.07166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07166"}},"official":{"repos":["embodied-agent-eval/embodied-agent-eval","embodied-agent-interface/embodied-agent-interface","embodied-agent-eval/embodied-agent-eval.github.io"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/swift-a-scalable-lightweight-infrastructure","slug":"swift-a-scalable-lightweight-infrastructure","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","date":"2024-08-10","arxiv_id":"2408.05517","repositories_listed":3,"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/swift-a-scalable-lightweight-infrastructure#ran","syntology_url":"https://syntology.ai/paper/2408.05517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05517"}},"official":{"repos":["modelscope/ms-swift","modelscope/swift"],"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/autohallusion-automatic-generation-of","slug":"autohallusion-automatic-generation-of","title":"AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models","date":"2024-06-16","arxiv_id":"2406.10900","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/autohallusion-automatic-generation-of#ran","syntology_url":"https://syntology.ai/paper/2406.10900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10900"}},"official":{"repos":["wuxiyang1996/AutoHallusion"],"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/prismatic-vlms-investigating-the-design-space","slug":"prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","arxiv_id":"2402.07865","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 4 unverified","sample_list":"/paper/prismatic-vlms-investigating-the-design-space#ran","syntology_url":"https://syntology.ai/paper/2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"official":{"repos":["tri-ml/prismatic-vlms","tri-ml/vlm-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/moe-llava-mixture-of-experts-for-large-vision","slug":"moe-llava-mixture-of-experts-for-large-vision","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","date":"2024-01-29","arxiv_id":"2401.15947","repositories_listed":3,"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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/moe-llava-mixture-of-experts-for-large-vision#ran","syntology_url":"https://syntology.ai/paper/2401.15947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15947"}},"official":{"repos":["PKU-YuanGroup/MoE-LLaVA"],"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/ragtruth-a-hallucination-corpus-for","slug":"ragtruth-a-hallucination-corpus-for","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","date":"2023-12-31","arxiv_id":"2401.00396","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ragtruth-a-hallucination-corpus-for#ran","syntology_url":"https://syntology.ai/paper/2401.00396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00396"}},"official":{"repos":["particlemedia/ragtruth"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-hallucinations-in-chinese-large","slug":"evaluating-hallucinations-in-chinese-large","title":"Evaluating Hallucinations in Chinese Large Language Models","date":"2023-10-05","arxiv_id":"2310.03368","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-hallucinations-in-chinese-large#ran","syntology_url":"https://syntology.ai/paper/2310.03368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03368"}},"official":{"repos":["xiami2019/halluqa"],"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/think-on-graph-deep-and-responsible-reasoning","slug":"think-on-graph-deep-and-responsible-reasoning","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","date":"2023-07-15","arxiv_id":"2307.07697","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":3,"n_no_contract":6,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 3 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/think-on-graph-deep-and-responsible-reasoning#ran","syntology_url":"https://syntology.ai/paper/2307.07697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07697"}},"official":{"repos":["gasolsun36/tog","idea-finai/tog"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/helma-a-large-scale-hallucination-evaluation","slug":"helma-a-large-scale-hallucination-evaluation","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","date":"2023-05-19","arxiv_id":"2305.11747","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/helma-a-large-scale-hallucination-evaluation#ran","syntology_url":"https://syntology.ai/paper/2305.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11747"}},"official":{"repos":["RUCAIBox/HaluEval","rucaibox/helma"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-chain-of-thought-reasoning-in","slug":"multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","arxiv_id":"2302.00923","repositories_listed":3,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multimodal-chain-of-thought-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2302.00923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00923"}},"official":{"repos":["amazon-science/mm-cot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dataset-distillation-via-factorization","slug":"dataset-distillation-via-factorization","title":"Dataset Distillation via Factorization","date":"2022-10-30","arxiv_id":"2210.16774","repositories_listed":3,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dataset-distillation-via-factorization#ran","syntology_url":"https://syntology.ai/paper/2210.16774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16774"}},"official":{"repos":["huage001/datasetfactorization"],"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/on-hallucinations-in-tomographic-image","slug":"on-hallucinations-in-tomographic-image","title":"On hallucinations in tomographic image reconstruction","date":"2020-12-01","arxiv_id":"2012.00646","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-hallucinations-in-tomographic-image#ran","syntology_url":"https://syntology.ai/paper/2012.00646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.00646"}},"official":null}},{"url":"/paper/discosg-towards-discourse-level-text-scene","slug":"discosg-towards-discourse-level-text-scene","title":"DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement","date":"2025-06-18","arxiv_id":"2506.15583","repositories_listed":2,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":9,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discosg-towards-discourse-level-text-scene#ran","syntology_url":"https://syntology.ai/paper/2506.15583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15583"}},"official":{"repos":["shaoqlin/discosg"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lettucedetect-a-hallucination-detection","slug":"lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","repositories_listed":2,"syntology":null},{"url":"/paper/fixing-imbalanced-attention-to-mitigate-in","slug":"fixing-imbalanced-attention-to-mitigate-in","title":"PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model","date":"2025-01-21","arxiv_id":"2501.12206","repositories_listed":2,"syntology":null},{"url":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","repositories_listed":2,"syntology":null},{"url":"/paper/differential-transformer","slug":"differential-transformer","title":"Differential Transformer","date":"2024-10-07","arxiv_id":"2410.05258","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":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/differential-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.05258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05258"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/2409-13694","slug":"2409-13694","title":"Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study","date":"2024-09-03","arxiv_id":"2409.13694","repositories_listed":2,"syntology":null},{"url":"/paper/2408-01800","slug":"2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","arxiv_id":"2408.01800","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-01800#ran","syntology_url":"https://syntology.ai/paper/2408.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01800"}},"official":{"repos":["OpenBMB/MiniCPM-o"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/maven-fact-a-large-scale-event-factuality","slug":"maven-fact-a-large-scale-event-factuality","title":"MAVEN-Fact: A Large-scale Event Factuality Detection Dataset","date":"2024-07-22","arxiv_id":"2407.15352","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/maven-fact-a-large-scale-event-factuality#ran","syntology_url":"https://syntology.ai/paper/2407.15352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15352"}},"official":{"repos":["lcy2723/maven-fact","THU-KEG/MAVEN-FACT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/finesure-fine-grained-summarization","slug":"finesure-fine-grained-summarization","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","date":"2024-07-01","arxiv_id":"2407.00908","repositories_listed":2,"syntology":null},{"url":"/paper/understanding-sounds-missing-the-questions","slug":"understanding-sounds-missing-the-questions","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","date":"2024-06-12","arxiv_id":"2406.08402","repositories_listed":2,"syntology":null},{"url":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"12 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domainrag-a-chinese-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2406.05654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05654"}},"official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crag-comprehensive-rag-benchmark#ran","syntology_url":"https://syntology.ai/paper/2406.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04744"}},"official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deem-diffusion-models-serve-as-the-eyes-of","slug":"deem-diffusion-models-serve-as-the-eyes-of","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","date":"2024-05-24","arxiv_id":"2405.15232","repositories_listed":2,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/deem-diffusion-models-serve-as-the-eyes-of#ran","syntology_url":"https://syntology.ai/paper/2405.15232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15232"}},"official":{"repos":["rainbowluocs/deem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-visual-language-modality-alignment","slug":"enhancing-visual-language-modality-alignment","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","date":"2024-05-24","arxiv_id":"2405.15973","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-visual-language-modality-alignment#ran","syntology_url":"https://syntology.ai/paper/2405.15973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15973"}},"official":{"repos":["umd-huang-lab/sima"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/refchecker-reference-based-fine-grained","slug":"refchecker-reference-based-fine-grained","title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14486","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":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) · 1 unverified","sample_list":"/paper/refchecker-reference-based-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2405.14486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14486"}},"official":{"repos":["amazon-science/refchecker"],"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/rag-and-rau-a-survey-on-retrieval-augmented","slug":"rag-and-rau-a-survey-on-retrieval-augmented","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","date":"2024-04-30","arxiv_id":"2404.19543","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rag-and-rau-a-survey-on-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2404.19543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19543"}},"official":{"repos":["2471023025/ralm_survey"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/towards-large-language-models-as-copilots-for","slug":"towards-large-language-models-as-copilots-for","title":"Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean","date":"2024-04-18","arxiv_id":"2404.12534","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-large-language-models-as-copilots-for#ran","syntology_url":"https://syntology.ai/paper/2404.12534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12534"}},"official":{"repos":["lean-dojo/leancopilot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/view-selection-for-3d-captioning-via","slug":"view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/view-selection-for-3d-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2404.07984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07984"}},"official":null}},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/urbanvlp-a-multi-granularity-vision-language","slug":"urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","arxiv_id":"2403.16831","repositories_listed":2,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":5,"n_honours":3,"n_violates":3,"n_no_contract":3,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/urbanvlp-a-multi-granularity-vision-language#ran","syntology_url":"https://syntology.ai/paper/2403.16831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16831"}},"official":{"repos":["citymind-lab/urbanvlp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/unsupervised-real-time-hallucination","slug":"unsupervised-real-time-hallucination","title":"Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models","date":"2024-03-11","arxiv_id":"2403.06448","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-real-time-hallucination#ran","syntology_url":"https://syntology.ai/paper/2403.06448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06448"}},"official":{"repos":["oneal2000/mind"],"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/halc-object-hallucination-reduction-via","slug":"halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","arxiv_id":"2403.00425","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/halc-object-hallucination-reduction-via#ran","syntology_url":"https://syntology.ai/paper/2403.00425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00425"}},"official":{"repos":["billchan226/halc","bradyfu/awesome-multimodal-large-language-models"],"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/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/seeing-is-believing-mitigating-hallucination#ran","syntology_url":"https://syntology.ai/paper/2402.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15300"}},"official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/g-retriever-retrieval-augmented-generation","slug":"g-retriever-retrieval-augmented-generation","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","date":"2024-02-12","arxiv_id":"2402.07630","repositories_listed":2,"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/g-retriever-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2402.07630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07630"}},"official":{"repos":["xiaoxinhe/g-retriever"],"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/poisonedrag-knowledge-poisoning-attacks-to","slug":"poisonedrag-knowledge-poisoning-attacks-to","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-02-12","arxiv_id":"2402.07867","repositories_listed":2,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":5,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/poisonedrag-knowledge-poisoning-attacks-to#ran","syntology_url":"https://syntology.ai/paper/2402.07867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07867"}},"official":{"repos":["sleeepeer/poisonedrag"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/unified-hallucination-detection-for","slug":"unified-hallucination-detection-for","title":"Unified Hallucination Detection for Multimodal Large Language Models","date":"2024-02-05","arxiv_id":"2402.03190","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unified-hallucination-detection-for#ran","syntology_url":"https://syntology.ai/paper/2402.03190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03190"}},"official":{"repos":["openkg-org/easydetect","zjunlp/easydetect"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skip-textbackslash-n-a-simple-method-to","slug":"skip-textbackslash-n-a-simple-method-to","title":"Skip \\n: A Simple Method to Reduce Hallucination in Large Vision-Language Models","date":"2024-02-02","arxiv_id":"2402.01345","repositories_listed":2,"syntology":null},{"url":"/paper/sh2-self-highlighted-hesitation-helps-you","slug":"sh2-self-highlighted-hesitation-helps-you","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","date":"2024-01-11","arxiv_id":"2401.05930","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"6 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; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/sh2-self-highlighted-hesitation-helps-you#ran","syntology_url":"https://syntology.ai/paper/2401.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05930"}},"official":{"repos":["0-kaikai-0/sh2","LUMIA-Group/SH2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/alleviating-hallucinations-of-large-language","slug":"alleviating-hallucinations-of-large-language","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","date":"2023-12-25","arxiv_id":"2312.15710","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"7 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/alleviating-hallucinations-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.15710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15710"}},"official":{"repos":["hiyouga/llama-factory","hillzhang1999/icd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/opera-alleviating-hallucination-in-multi","slug":"opera-alleviating-hallucination-in-multi","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","date":"2023-11-29","arxiv_id":"2311.17911","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"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) · 6 unverified","sample_list":"/paper/opera-alleviating-hallucination-in-multi#ran","syntology_url":"https://syntology.ai/paper/2311.17911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17911"}},"official":{"repos":["shikiw/opera"],"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","unlocated"]}}},{"url":"/paper/enhancing-uncertainty-based-hallucination","slug":"enhancing-uncertainty-based-hallucination","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","date":"2023-11-22","arxiv_id":"2311.13230","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"11 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-uncertainty-based-hallucination#ran","syntology_url":"https://syntology.ai/paper/2311.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13230"}},"official":{"repos":["zthang/focus"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/distil-whisper-robust-knowledge-distillation","slug":"distil-whisper-robust-knowledge-distillation","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","date":"2023-11-01","arxiv_id":"2311.00430","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/distil-whisper-robust-knowledge-distillation#ran","syntology_url":"https://syntology.ai/paper/2311.00430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00430"}},"official":{"repos":["huggingface/distil-whisper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ferret-refer-and-ground-anything-anywhere-at","slug":"ferret-refer-and-ground-anything-anywhere-at","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","date":"2023-10-11","arxiv_id":"2310.07704","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ferret-refer-and-ground-anything-anywhere-at#ran","syntology_url":"https://syntology.ai/paper/2310.07704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07704"}},"official":{"repos":["apple/ml-ferret"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-large-language-models-as-ai","slug":"benchmarking-large-language-models-as-ai","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","date":"2023-10-05","arxiv_id":"2310.03302","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/benchmarking-large-language-models-as-ai#ran","syntology_url":"https://syntology.ai/paper/2310.03302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03302"}},"official":{"repos":["snap-stanford/mlagentbench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/freshllms-refreshing-large-language-models","slug":"freshllms-refreshing-large-language-models","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","date":"2023-10-05","arxiv_id":"2310.03214","repositories_listed":2,"syntology":null},{"url":"/paper/halle-switch-rethinking-and-controlling","slug":"halle-switch-rethinking-and-controlling","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","date":"2023-10-03","arxiv_id":"2310.01779","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"6 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/halle-switch-rethinking-and-controlling#ran","syntology_url":"https://syntology.ai/paper/2310.01779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01779"}},"official":{"repos":["bronyayang/HallE_Switch","bronyayang/halle_control"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mmicl-empowering-vision-language-model-with","slug":"mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","date":"2023-09-14","arxiv_id":"2309.07915","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}},"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vigc-visual-instruction-generation-and","slug":"vigc-visual-instruction-generation-and","title":"VIGC: Visual Instruction Generation and Correction","date":"2023-08-24","arxiv_id":"2308.12714","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vigc-visual-instruction-generation-and#ran","syntology_url":"https://syntology.ai/paper/2308.12714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12714"}},"official":{"repos":["opendatalab/vigc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-augmented-generation-and","slug":"retrieval-augmented-generation-and","title":"Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical Education","date":"2023-08-01","arxiv_id":"2308.00479","repositories_listed":2,"syntology":null},{"url":"/paper/unleashing-cognitive-synergy-in-large","slug":"unleashing-cognitive-synergy-in-large","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","date":"2023-07-11","arxiv_id":"2307.05300","repositories_listed":2,"syntology":null},{"url":"/paper/toolqa-a-dataset-for-llm-question-answering-1","slug":"toolqa-a-dataset-for-llm-question-answering-1","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","date":"2023-06-23","arxiv_id":"2306.13304","repositories_listed":2,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"14 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/toolqa-a-dataset-for-llm-question-answering-1#ran","syntology_url":"https://syntology.ai/paper/2306.13304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13304"}},"official":{"repos":["night-chen/toolqa"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-human-like-translation-strategy","slug":"exploring-human-like-translation-strategy","title":"Exploring Human-Like Translation Strategy with Large Language Models","date":"2023-05-06","arxiv_id":"2305.04118","repositories_listed":2,"syntology":null},{"url":"/paper/gpt-ner-named-entity-recognition-via-large","slug":"gpt-ner-named-entity-recognition-via-large","title":"GPT-NER: Named Entity Recognition via Large Language Models","date":"2023-04-20","arxiv_id":"2304.10428","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-ner-named-entity-recognition-via-large#ran","syntology_url":"https://syntology.ai/paper/2304.10428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10428"}},"official":{"repos":["shuhewang1998/gpt-ner"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-language-models-can-rate-news-outlet","slug":"large-language-models-can-rate-news-outlet","title":"Accuracy and Political Bias of News Source Credibility Ratings by Large Language Models","date":"2023-04-01","arxiv_id":"2304.00228","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-are-versatile","slug":"large-language-models-are-versatile","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","date":"2023-01-31","arxiv_id":"2301.13808","repositories_listed":2,"syntology":null},{"url":"/paper/mqag-multiple-choice-question-answering-and","slug":"mqag-multiple-choice-question-answering-and","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","date":"2023-01-28","arxiv_id":"2301.12307","repositories_listed":2,"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/mqag-multiple-choice-question-answering-and#ran","syntology_url":"https://syntology.ai/paper/2301.12307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12307"}},"official":{"repos":["potsawee/mqag0"],"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/interleaving-retrieval-with-chain-of-thought","slug":"interleaving-retrieval-with-chain-of-thought","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","date":"2022-12-20","arxiv_id":"2212.10509","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interleaving-retrieval-with-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2212.10509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10509"}},"official":{"repos":["stonybrooknlp/ircot"],"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/harim-evaluating-summary-quality-with","slug":"harim-evaluating-summary-quality-with","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","date":"2022-11-22","arxiv_id":"2211.12118","repositories_listed":2,"syntology":null},{"url":"/paper/style-hallucinated-dual-consistency-learning","slug":"style-hallucinated-dual-consistency-learning","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","date":"2022-04-06","arxiv_id":"2204.02548","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/style-hallucinated-dual-consistency-learning#ran","syntology_url":"https://syntology.ai/paper/2204.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02548"}},"official":{"repos":["helioszhao/shade"],"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/towards-an-end-to-end-framework-for-flow","slug":"towards-an-end-to-end-framework-for-flow","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","date":"2022-04-06","arxiv_id":"2204.02663","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-an-end-to-end-framework-for-flow#ran","syntology_url":"https://syntology.ai/paper/2204.02663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02663"}},"official":{"repos":["MCG-NKU/E2FGVI"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-token-level-reference-free-hallucination","slug":"a-token-level-reference-free-hallucination","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","date":"2021-04-18","arxiv_id":"2104.08704","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/a-token-level-reference-free-hallucination#ran","syntology_url":"https://syntology.ai/paper/2104.08704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08704"}},"official":{"repos":["microsoft/HaDes"],"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/detecting-hallucinated-content-in-conditional-1","slug":"detecting-hallucinated-content-in-conditional-1","title":"Detecting Hallucinated Content in Conditional Neural Sequence Generation","date":"2020-11-05","arxiv_id":"2011.02593","repositories_listed":2,"syntology":null},{"url":"/paper/bigprior-towards-decoupling-learned-prior","slug":"bigprior-towards-decoupling-learned-prior","title":"BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration","date":"2020-11-03","arxiv_id":"2011.01406","repositories_listed":2,"syntology":null},{"url":"/paper/3d-sketch-aware-semantic-scene-completion-via","slug":"3d-sketch-aware-semantic-scene-completion-via","title":"3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior","date":"2020-03-31","arxiv_id":"2003.14052","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/3d-sketch-aware-semantic-scene-completion-via#ran","syntology_url":"https://syntology.ai/paper/2003.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.14052"}},"official":null}},{"url":"/paper/hallucinet-ing-spatiotemporal-representations","slug":"hallucinet-ing-spatiotemporal-representations","title":"HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN","date":"2019-12-10","arxiv_id":"1912.04430","repositories_listed":2,"syntology":null},{"url":"/paper/context-patch-face-hallucination-based-on","slug":"context-patch-face-hallucination-based-on","title":"Context-Patch Face Hallucination Based on Thresholding Locality-constrained Representation and Reproducing Learning","date":"2018-09-03","arxiv_id":"1809.00665","repositories_listed":2,"syntology":null},{"url":"/paper/brain-mri-image-super-resolution-using-phase","slug":"brain-mri-image-super-resolution-using-phase","title":"Brain MRI Image Super Resolution using Phase Stretch Transform and Transfer Learning","date":"2018-07-31","arxiv_id":"1807.11643","repositories_listed":2,"syntology":null},{"url":"/paper/mitigating-object-hallucinations-via-sentence","slug":"mitigating-object-hallucinations-via-sentence","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","date":"2025-07-16","arxiv_id":"2507.12455","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-object-hallucinations-via-sentence#ran","syntology_url":"https://syntology.ai/paper/2507.12455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.12455"}},"official":{"repos":["pspdada/SENTINEL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uqlm-a-python-package-for-uncertainty","slug":"uqlm-a-python-package-for-uncertainty","title":"UQLM: A Python Package for Uncertainty Quantification in Large Language Models","date":"2025-07-08","arxiv_id":"2507.06196","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/uqlm-a-python-package-for-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2507.06196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06196"}},"official":{"repos":["cvs-health/uqlm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-hallucination-of-large-vision","slug":"mitigating-hallucination-of-large-vision","title":"Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration","date":"2025-06-26","arxiv_id":"2506.21509","repositories_listed":1,"syntology":null},{"url":"/paper/knowrl-exploring-knowledgeable-reinforcement","slug":"knowrl-exploring-knowledgeable-reinforcement","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","date":"2025-06-24","arxiv_id":"2506.19807","repositories_listed":1,"syntology":null},{"url":"/paper/abstract-meaning-representation-for-hospital","slug":"abstract-meaning-representation-for-hospital","title":"Abstract Meaning Representation for Hospital Discharge Summarization","date":"2025-06-17","arxiv_id":"2506.14101","repositories_listed":1,"syntology":null},{"url":"/paper/stress-testing-multimodal-foundation-models","slug":"stress-testing-multimodal-foundation-models","title":"Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning","date":"2025-06-16","arxiv_id":"2506.13051","repositories_listed":1,"syntology":null},{"url":"/paper/difffusr-super-resolution-of-all-sentinel-2","slug":"difffusr-super-resolution-of-all-sentinel-2","title":"DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion Models","date":"2025-06-13","arxiv_id":"2506.11764","repositories_listed":1,"syntology":null},{"url":"/paper/revisit-what-you-see-disclose-language-prior","slug":"revisit-what-you-see-disclose-language-prior","title":"Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs","date":"2025-06-11","arxiv_id":"2506.09522","repositories_listed":1,"syntology":null},{"url":"/paper/step-by-step-instructions-and-a-simple","slug":"step-by-step-instructions-and-a-simple","title":"Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs","date":"2025-06-11","arxiv_id":"2506.09983","repositories_listed":1,"syntology":null},{"url":"/paper/vicrit-a-verifiable-reinforcement-learning","slug":"vicrit-a-verifiable-reinforcement-learning","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs","date":"2025-06-11","arxiv_id":"2506.10128","repositories_listed":1,"syntology":null},{"url":"/paper/second-mitigating-perceptual-hallucination-in","slug":"second-mitigating-perceptual-hallucination-in","title":"SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding","date":"2025-06-10","arxiv_id":"2506.08391","repositories_listed":1,"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/second-mitigating-perceptual-hallucination-in#ran","syntology_url":"https://syntology.ai/paper/2506.08391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08391"}},"official":{"repos":["aidaslab/second"],"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","unlocated"]}}},{"url":"/paper/medchat-a-multi-agent-framework-for","slug":"medchat-a-multi-agent-framework-for","title":"MedChat: A Multi-Agent Framework for Multimodal Diagnosis with Large Language Models","date":"2025-06-09","arxiv_id":"2506.07400","repositories_listed":1,"syntology":null},{"url":"/paper/golfer-smaller-lm-generated-documents","slug":"golfer-smaller-lm-generated-documents","title":"GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval","date":"2025-06-05","arxiv_id":"2506.04762","repositories_listed":1,"syntology":null},{"url":"/paper/joint-evaluation-of-answer-and-reasoning","slug":"joint-evaluation-of-answer-and-reasoning","title":"Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models","date":"2025-06-05","arxiv_id":"2506.04832","repositories_listed":1,"syntology":null},{"url":"/paper/safe-enhancing-mathematical-reasoning-in","slug":"safe-enhancing-mathematical-reasoning-in","title":"Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification","date":"2025-06-05","arxiv_id":"2506.04592","repositories_listed":1,"syntology":null},{"url":"/paper/owmm-agent-open-world-mobile-manipulation","slug":"owmm-agent-open-world-mobile-manipulation","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis","date":"2025-06-04","arxiv_id":"2506.04217","repositories_listed":1,"syntology":null},{"url":"/paper/flysearch-exploring-how-vision-language","slug":"flysearch-exploring-how-vision-language","title":"FlySearch: Exploring how vision-language models explore","date":"2025-06-03","arxiv_id":"2506.02896","repositories_listed":1,"syntology":null}],"syntology_records":61,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":276,"papers_where_code_ran_first_page":"/task/hallucination/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":19,"url":"/task/hallucination/papers/2","json":"/task/hallucination/papers/2.json","rows":100},{"order":"archive","page":3,"of":19,"url":"/task/hallucination/papers/3","json":"/task/hallucination/papers/3.json","rows":100},{"order":"archive","page":4,"of":19,"url":"/task/hallucination/papers/4","json":"/task/hallucination/papers/4.json","rows":100},{"order":"archive","page":5,"of":19,"url":"/task/hallucination/papers/5","json":"/task/hallucination/papers/5.json","rows":100},{"order":"archive","page":6,"of":19,"url":"/task/hallucination/papers/6","json":"/task/hallucination/papers/6.json","rows":100},{"order":"archive","page":7,"of":19,"url":"/task/hallucination/papers/7","json":"/task/hallucination/papers/7.json","rows":100},{"order":"archive","page":8,"of":19,"url":"/task/hallucination/papers/8","json":"/task/hallucination/papers/8.json","rows":100},{"order":"archive","page":9,"of":19,"url":"/task/hallucination/papers/9","json":"/task/hallucination/papers/9.json","rows":100},{"order":"archive","page":10,"of":19,"url":"/task/hallucination/papers/10","json":"/task/hallucination/papers/10.json","rows":100},{"order":"archive","page":11,"of":19,"url":"/task/hallucination/papers/11","json":"/task/hallucination/papers/11.json","rows":100},{"order":"archive","page":12,"of":19,"url":"/task/hallucination/papers/12","json":"/task/hallucination/papers/12.json","rows":100},{"order":"archive","page":13,"of":19,"url":"/task/hallucination/papers/13","json":"/task/hallucination/papers/13.json","rows":100},{"order":"archive","page":14,"of":19,"url":"/task/hallucination/papers/14","json":"/task/hallucination/papers/14.json","rows":100},{"order":"archive","page":15,"of":19,"url":"/task/hallucination/papers/15","json":"/task/hallucination/papers/15.json","rows":100},{"order":"archive","page":16,"of":19,"url":"/task/hallucination/papers/16","json":"/task/hallucination/papers/16.json","rows":100},{"order":"archive","page":17,"of":19,"url":"/task/hallucination/papers/17","json":"/task/hallucination/papers/17.json","rows":100},{"order":"archive","page":18,"of":19,"url":"/task/hallucination/papers/18","json":"/task/hallucination/papers/18.json","rows":100},{"order":"archive","page":19,"of":19,"url":"/task/hallucination/papers/19","json":"/task/hallucination/papers/19.json","rows":16},{"order":"ran","page":1,"of":3,"url":"/task/hallucination/papers/ran/1","json":"/task/hallucination/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/hallucination/papers/ran/2","json":"/task/hallucination/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/hallucination/papers/ran/3","json":"/task/hallucination/papers/ran/3.json","rows":76}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a2c671c1da0c971b59c0f1c6dbea9f0b3d27bf69ac3991ed2de0b5476a1e1e04","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}