{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":42,"tagged_in_all":71,"items":[{"url":"/paper/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":9,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/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":6,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/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":14,"n_unverified":8,"n_pointer_only":8}},{"url":"/paper/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_unverified":2,"n_pointer_only":2}},{"url":"/paper/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","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_unverified":5,"n_pointer_only":0}},{"url":"/paper/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_unverified":6,"n_pointer_only":17}},{"url":"/paper/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_unverified":1,"n_pointer_only":8}},{"url":"/paper/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":5,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":4}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","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":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":8}},{"url":"/paper/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","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_unverified":3,"n_pointer_only":3}},{"url":"/paper/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_unverified":1,"n_pointer_only":7}},{"url":"/paper/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","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_unverified":4,"n_pointer_only":17}}],"syntology_records":18,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}