{"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":"/dataset/hallusionbench","name":"HallusionBench","full_name":null,"description_markdown":"Large language models (LLMs), after being aligned with vision models and integrated into vision-language models (VLMs), can bring impressive improvement in image reasoning tasks. This was shown by the recently released GPT-4V(ison), LLaVA-1.5, etc. However, the strong language prior in these SOTA LVLMs can be a double-edged sword: they may ignore the image context and solely rely on the (even contradictory) language prior for reasoning. In contrast, the vision modules in VLMs are weaker than LLMs and may result in misleading visual representations, which are then translated to confident mistakes by LLMs. \r\n\r\nTo study these two types of VLM mistakes, i.e., language hallucination and visual illusion, we curated HallusionBench, an image-context reasoning benchmark that is still challenging to even GPT-4V and LLaVA-1.5. We provide a detailed analysis of examples in HallusionBench, which sheds novel insights on the illusion or hallucination of VLMs and how to improve them in the future.","description_withheld":null,"homepage":"https://github.com/tianyi-lab/HallusionBench","introduced_date":"2023-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/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","first_author":"Tianrui Guan","url":null},"license":{"name":"BSD 3-Clause License","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["HallusionBench"],"data_loaders":[{"repo":"https://github.com/tianyi-lab/hallusionbench","url":"https://github.com/tianyi-lab/hallusionbench","frameworks":["pytorch"]}],"num_papers_in_archive":53,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-vqa-on-3","task":"Visual Question Answering (VQA)","dataset_variant":"HallusionBench","rows":4,"metrics":["Question Pair Acc\t","Question Pair Acc"],"first_row_in_archive_order":{"model":"GPT-4V","paper":"/paper/hallusionbench-you-see-what-you-think-or-you","metrics":{"Question Pair Acc\t":"12.2047"},"code_links":[{"title":"codelion/adaptive-classifier","url":"https://github.com/codelion/adaptive-classifier"},{"title":"tianyi-lab/hallusionbench","url":"https://github.com/tianyi-lab/hallusionbench"},{"title":"FuxiaoLiu/LRV-Instruction","url":"https://github.com/FuxiaoLiu/LRV-Instruction"},{"title":"fuxiaoliu/mmc","url":"https://github.com/fuxiaoliu/mmc"},{"title":"FuxiaoLiu/VisualNews-Repository","url":"https://github.com/FuxiaoLiu/VisualNews-Repository"},{"title":"dongping-chen/mllm-as-a-judge","url":"https://github.com/dongping-chen/mllm-as-a-judge"},{"title":"zli12321/qa_metrics","url":"https://github.com/zli12321/qa_metrics"},{"title":"wuxiyang1996/AutoHallusion","url":"https://github.com/wuxiyang1996/AutoHallusion"},{"title":"zli12321/videohallu","url":"https://github.com/zli12321/videohallu"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/mplug-owl-modularization-empowers-large","slug":"mplug-owl-modularization-empowers-large","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","date":"2023-04-27","arxiv_id":"2304.14178","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/mplug-owl-modularization-empowers-large","slug":"mplug-owl-modularization-empowers-large","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","date":"2023-04-27","arxiv_id":"2304.14178","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/hallusionbench/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/hallusionbench/papers/ran/1","json":"/dataset/hallusionbench/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":8,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/visual-question-answering-vqa-on-3","since_archive":"/sota/visual-question-answering-vqa-on-3#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"f4207af0e7378b4180efd9228222e028bd053214f3a7f49e7f0996a5a0bd79ec","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}