{"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/object-hallucination","name":"Object Hallucination","slug":"object-hallucination","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":71,"papers_with_code":42,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/visual-question-answering-1","name":"Visual Question Answering"}],"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":1,"rows_per_page":100,"shown":71,"of":71,"of_with_code":42,"tagged_in_all":71,"counts":{"archive_papers_tagged":71,"with_a_code_link":42,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":71,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/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/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/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/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/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/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/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/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/retrieval-visual-contrastive-decoding-to","slug":"retrieval-visual-contrastive-decoding-to","title":"Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models","date":"2025-05-26","arxiv_id":"2505.20569","repositories_listed":1,"syntology":null},{"url":"/paper/cafe-unifying-representation-and-generation","slug":"cafe-unifying-representation-and-generation","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","date":"2025-03-25","arxiv_id":"2503.19900","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cafe-unifying-representation-and-generation#ran","syntology_url":"https://syntology.ai/paper/2503.19900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19900"}},"official":{"repos":["haoyu-bu/CAFe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/clearsight-visual-signal-enhancement-for","slug":"clearsight-visual-signal-enhancement-for","title":"ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models","date":"2025-03-17","arxiv_id":"2503.13107","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/clearsight-visual-signal-enhancement-for#ran","syntology_url":"https://syntology.ai/paper/2503.13107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13107"}},"official":{"repos":["ustc-hyin/ClearSight"],"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/truthprint-mitigating-lvlm-object","slug":"truthprint-mitigating-lvlm-object","title":"TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention","date":"2025-03-13","arxiv_id":"2503.10602","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-hallucinations-in-large-vision-4","slug":"mitigating-hallucinations-in-large-vision-4","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","date":"2025-02-28","arxiv_id":"2502.20750","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-hallucinations-in-large-vision-4#ran","syntology_url":"https://syntology.ai/paper/2502.20750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20750"}},"official":{"repos":["jiaqi5598/adavib"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-encoders-already-know-what-they-see","slug":"vision-encoders-already-know-what-they-see","title":"Vision-Encoders (Already) Know What They See: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore","date":"2025-02-27","arxiv_id":"2502.20034","repositories_listed":1,"syntology":null},{"url":"/paper/hallucinogen-a-benchmark-for-evaluating","slug":"hallucinogen-a-benchmark-for-evaluating","title":"HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models","date":"2024-12-29","arxiv_id":"2412.20622","repositories_listed":1,"syntology":null},{"url":"/paper/extract-free-dense-misalignment-from-clip","slug":"extract-free-dense-misalignment-from-clip","title":"Extract Free Dense Misalignment from CLIP","date":"2024-12-24","arxiv_id":"2412.18404","repositories_listed":1,"syntology":null},{"url":"/paper/unified-triplet-level-hallucination","slug":"unified-triplet-level-hallucination","title":"Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models","date":"2024-10-30","arxiv_id":"2410.23114","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-object-hallucination-via","slug":"mitigating-object-hallucination-via","title":"Mitigating Object Hallucination via Concentric Causal Attention","date":"2024-10-21","arxiv_id":"2410.15926","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mitigating-object-hallucination-via#ran","syntology_url":"https://syntology.ai/paper/2410.15926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15926"}},"official":{"repos":["xing0047/cca-llava"],"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/mitigating-hallucinations-in-large-vision-2","slug":"mitigating-hallucinations-in-large-vision-2","title":"Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding","date":"2024-10-17","arxiv_id":"2410.13321","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-and-mitigating-object","slug":"investigating-and-mitigating-object","title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","date":"2024-10-04","arxiv_id":"2410.03176","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/investigating-and-mitigating-object#ran","syntology_url":"https://syntology.ai/paper/2410.03176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03176"}},"official":{"repos":["yufang-liu/clip_hallucination"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-multimodal-hallucination-with","slug":"understanding-multimodal-hallucination-with","title":"Understanding Multimodal Hallucination with Parameter-Free Representation Alignment","date":"2024-09-02","arxiv_id":"2409.01151","repositories_listed":1,"syntology":null},{"url":"/paper/multi-object-hallucination-in-vision-language","slug":"multi-object-hallucination-in-vision-language","title":"Multi-Object Hallucination in Vision-Language Models","date":"2024-07-08","arxiv_id":"2407.06192","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-object-hallucination-in-vision-language#ran","syntology_url":"https://syntology.ai/paper/2407.06192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06192"}},"official":{"repos":["sled-group/moh"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/think-before-you-act-a-two-stage-framework","slug":"think-before-you-act-a-two-stage-framework","title":"Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks","date":"2024-05-27","arxiv_id":"2405.16860","repositories_listed":1,"syntology":null},{"url":"/paper/logical-closed-loop-uncovering-object","slug":"logical-closed-loop-uncovering-object","title":"Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models","date":"2024-02-18","arxiv_id":"2402.11622","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/logical-closed-loop-uncovering-object#ran","syntology_url":"https://syntology.ai/paper/2402.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11622"}},"official":{"repos":["hyperwjf/logiccheckgpt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/efuf-efficient-fine-grained-unlearning","slug":"efuf-efficient-fine-grained-unlearning","title":"EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models","date":"2024-02-15","arxiv_id":"2402.09801","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/efuf-efficient-fine-grained-unlearning#ran","syntology_url":"https://syntology.ai/paper/2402.09801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09801"}},"official":{"repos":["starreeze/efuf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/instruction-makes-a-difference","slug":"instruction-makes-a-difference","title":"Instruction Makes a Difference","date":"2024-02-01","arxiv_id":"2402.00453","repositories_listed":1,"syntology":null},{"url":"/paper/towards-stable-and-faithful-inpainting","slug":"towards-stable-and-faithful-inpainting","title":"Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency","date":"2023-12-08","arxiv_id":"2312.04831","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":4,"n_no_contract":5,"n_pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 4 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-stable-and-faithful-inpainting#ran","syntology_url":"https://syntology.ai/paper/2312.04831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04831"}},"official":{"repos":["yikai-wang/asuka-misato"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-fine-grained-hallucination-by-fine","slug":"mitigating-fine-grained-hallucination-by-fine","title":"Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites","date":"2023-12-04","arxiv_id":"2312.01701","repositories_listed":1,"syntology":null},{"url":"/paper/from-clip-to-dino-visual-encoders-shout-in","slug":"from-clip-to-dino-visual-encoders-shout-in","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","date":"2023-10-13","arxiv_id":"2310.08825","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-mitigating-object-hallucination","slug":"analyzing-and-mitigating-object-hallucination","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","date":"2023-10-01","arxiv_id":"2310.00754","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analyzing-and-mitigating-object-hallucination#ran","syntology_url":"https://syntology.ai/paper/2310.00754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00754"}},"official":{"repos":["yiyangzhou/lure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/detecting-and-preventing-hallucinations-in","slug":"detecting-and-preventing-hallucinations-in","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","date":"2023-08-11","arxiv_id":"2308.06394","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-lvlm-ehub-early-multimodal-experiments","slug":"tiny-lvlm-ehub-early-multimodal-experiments","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models","date":"2023-08-07","arxiv_id":"2308.03729","repositories_listed":1,"syntology":null},{"url":"/paper/transferable-decoding-with-visual-entities","slug":"transferable-decoding-with-visual-entities","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","date":"2023-07-31","arxiv_id":"2307.16525","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transferable-decoding-with-visual-entities#ran","syntology_url":"https://syntology.ai/paper/2307.16525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16525"}},"official":{"repos":["feielysia/viecap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lvlm-ehub-a-comprehensive-evaluation","slug":"lvlm-ehub-a-comprehensive-evaluation","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","date":"2023-06-15","arxiv_id":"2306.09265","repositories_listed":1,"syntology":null},{"url":"/paper/plausible-may-not-be-faithful-probing-object","slug":"plausible-may-not-be-faithful-probing-object","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","date":"2022-10-14","arxiv_id":"2210.07688","repositories_listed":1,"syntology":null},{"url":"/paper/let-there-be-a-clock-on-the-beach-reducing","slug":"let-there-be-a-clock-on-the-beach-reducing","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","date":"2021-10-04","arxiv_id":"2110.01705","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/let-there-be-a-clock-on-the-beach-reducing#ran","syntology_url":"https://syntology.ai/paper/2110.01705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01705"}},"official":{"repos":["furkanbiten/object-bias"],"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/hyperpocket-generative-point-cloud-completion","slug":"hyperpocket-generative-point-cloud-completion","title":"HyperPocket: Generative Point Cloud Completion","date":"2021-02-11","arxiv_id":"2102.05973","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-image-captioning-models-beyond","slug":"understanding-image-captioning-models-beyond","title":"Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models","date":"2020-01-04","arxiv_id":"2001.01037","repositories_listed":1,"syntology":null},{"url":"/paper/object-hallucination-in-image-captioning","slug":"object-hallucination-in-image-captioning","title":"Object Hallucination in Image Captioning","date":"2018-09-06","arxiv_id":"1809.02156","repositories_listed":1,"syntology":null},{"url":null,"slug":"reducing-object-hallucination-in-large-audio","title":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding","date":"2025-06-08","arxiv_id":"2506.07233","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-instruction-bottleneck-tuning","title":"Visual Instruction Bottleneck Tuning","date":"2025-05-20","arxiv_id":"2505.13946","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-analysis-for-visual-object","title":"A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models","date":"2025-05-04","arxiv_id":"2505.01958","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-box-visual-prompt-engineering-for","title":"Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models","date":"2025-04-30","arxiv_id":"2504.21559","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnipaint-mastering-object-oriented-editing","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","date":"2025-03-11","arxiv_id":"2503.08677","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-what-s-not-there-spurious-correlation","title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs","date":"2025-03-11","arxiv_id":"2503.08884","repositories_listed":0,"syntology":null},{"url":null,"slug":"eazy-eliminating-hallucinations-in-lvlms-by","title":"EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens","date":"2025-03-10","arxiv_id":"2503.07772","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-background-information-in","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","date":"2025-02-21","arxiv_id":"2502.15389","repositories_listed":0,"syntology":null},{"url":null,"slug":"cutpaste-find-efficient-multimodal","title":"CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base","date":"2025-02-18","arxiv_id":"2502.12591","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-object-hallucinations-in-large-1","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","date":"2025-02-04","arxiv_id":"2502.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"poison-as-cure-visual-noise-for-mitigating","title":"Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs","date":"2025-01-31","arxiv_id":"2501.19164","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-hallucination-in-large-vision","title":"Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities","date":"2025-01-25","arxiv_id":"2501.15046","repositories_listed":0,"syntology":null},{"url":null,"slug":"ict-image-object-cross-level-trusted","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","date":"2024-11-22","arxiv_id":"2411.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"damro-dive-into-the-attention-mechanism-of","title":"DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination","date":"2024-10-06","arxiv_id":"2410.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-object-grounding-really-reduce","title":"Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?","date":"2024-06-20","arxiv_id":"2406.14492","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-more-details-always-introduce-more","title":"Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?","date":"2024-06-18","arxiv_id":"2406.12663","repositories_listed":0,"syntology":null},{"url":"/paper/mitigating-object-hallucination-via-data","slug":"mitigating-object-hallucination-via-data","title":"Data-augmented phrase-level alignment for mitigating object hallucination","date":"2024-05-28","arxiv_id":"2405.18654","repositories_listed":0,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-object-hallucination-via-data#ran","syntology_url":"https://syntology.ai/paper/2405.18654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18654"}},"official":null}},{"url":null,"slug":"ritual-random-image-transformations-as-a","title":"RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models","date":"2024-05-28","arxiv_id":"2405.17821","repositories_listed":0,"syntology":null},{"url":null,"slug":"aloha-a-new-measure-for-hallucination-in","title":"ALOHa: A New Measure for Hallucination in Captioning Models","date":"2024-04-03","arxiv_id":"2404.02904","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-assessment-of-recent-large","title":"Effectiveness Assessment of Recent Large Vision-Language Models","date":"2024-03-07","arxiv_id":"2403.04306","repositories_listed":0,"syntology":null},{"url":"/paper/groundhog-grounding-large-language-models-to","slug":"groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","arxiv_id":"2402.16846","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-object-hallucination-in-large","title":"Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance","date":"2024-02-13","arxiv_id":"2402.08680","repositories_listed":0,"syntology":null},{"url":null,"slug":"knvqa-a-benchmark-for-evaluation-knowledge","title":"KNVQA: A Benchmark for evaluation knowledge-based VQA","date":"2023-11-21","arxiv_id":"2311.12639","repositories_listed":0,"syntology":null},{"url":null,"slug":"negative-object-presence-evaluation-nope-to","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","date":"2023-10-09","arxiv_id":"2310.05338","repositories_listed":0,"syntology":null},{"url":"/paper/simple-token-level-confidence-improves","slug":"simple-token-level-confidence-improves","title":"Simple Token-Level Confidence Improves Caption Correctness","date":"2023-05-11","arxiv_id":"2305.07021","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-approaches-on-image-captioning","title":"Deep Learning Approaches on Image Captioning: A Review","date":"2022-01-31","arxiv_id":"2201.12944","repositories_listed":0,"syntology":null},{"url":null,"slug":"consensus-graph-representation-learning-for","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","date":"2021-12-02","arxiv_id":"2112.00974","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-graph-learning-for-grounded-video","title":"Relational Graph Learning for Grounded Video Description Generation","date":"2021-12-02","arxiv_id":"2112.00967","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-ve-seen-things-you-people-wouldn-t-believe","title":"``I've Seen Things You People Wouldn't Believe'': Hallucinating Entities in GuessWhat?!","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":22,"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":18,"papers_where_code_ran_first_page":"/task/object-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":"ran","page":1,"of":1,"url":"/task/object-hallucination/papers/ran/1","json":"/task/object-hallucination/papers/ran/1.json","rows":18}],"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":"03f2571b77f1ea6f063bff6f9b8585f42befd8c7e97ad45cb6f7a3a958775a3a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}