{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCYNG54FMM74BLASM5OMVQKGDV","short_pith_number":"pith:MCYNG54F","schema_version":"1.0","canonical_sha256":"60b0d37785633fc0ac12675ccac1461d5c6257f36b2a5a10468ee6d6560931d5","source":{"kind":"arxiv","id":"2402.00253","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Hallucination in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large vision-language models generate text that conflicts with input images, and this survey defines the problem while reviewing its symptoms, benchmarks, causes, and fixes.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Chen, Hanchao Liu, Ke Wang, Liping Hou, Rongjun Li, Wei Peng, Wenyuan Xue, Xiutian Zhao, Yifei Chen","submitted_at":"2024-02-01T00:33:21Z","abstract_excerpt":"Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs. In this comprehensive survey, we dissect LVLM-related hallucinations in an attempt to establish an overview and facilitate future mitigation. Our scrutiny starts with a clarification of the concept of hallucinations in LVLMs, presenting a variety of hallu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2402.00253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-01T00:33:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"33a9a211515ced3e215194accef8df66483c182165a90f379bf8d027480135ce","abstract_canon_sha256":"58e98477621291f8569dc0c279bd252a0b496b574d21a26e9188f320d8d2a5b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:33:37.171109Z","signature_b64":"pwJmCzGfSskX+ZdElXj8nnHLsPO3sNJ5z3nBys0FjZ1BDUOfY4RRYPalzt4vZoT5st621ASAjDvsBJ71iXRZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60b0d37785633fc0ac12675ccac1461d5c6257f36b2a5a10468ee6d6560931d5","last_reissued_at":"2026-05-18T04:33:37.170404Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:33:37.170404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Hallucination in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large vision-language models generate text that conflicts with input images, and this survey defines the problem while reviewing its symptoms, benchmarks, causes, and fixes.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Chen, Hanchao Liu, Ke Wang, Liping Hou, Rongjun Li, Wei Peng, Wenyuan Xue, Xiutian Zhao, Yifei Chen","submitted_at":"2024-02-01T00:33:21Z","abstract_excerpt":"Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs. In this comprehensive survey, we dissect LVLM-related hallucinations in an attempt to establish an overview and facilitate future mitigation. Our scrutiny starts with a clarification of the concept of hallucinations in LVLMs, presenting a variety of hallu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Hallucination, defined as the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs, and this survey establishes an overview to facilitate future mitigation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That hallucinations can be consistently defined and isolated across diverse LVLM architectures and tasks without significant overlap with other error types such as reasoning failures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large vision-language models generate text that conflicts with input images, and this survey defines the problem while reviewing its symptoms, benchmarks, causes, and fixes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"94927963cf9c0a8d68a781ebc484168fa21c4d54e9d5a0bf6136a10c04d26c83"},"source":{"id":"2402.00253","kind":"arxiv","version":2},"verdict":{"id":"bdbc8482-dc4c-481d-a809-04ade0131e21","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:05:38.517168Z","strongest_claim":"Hallucination, defined as the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs, and this survey establishes an overview to facilitate future mitigation.","one_line_summary":"This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That hallucinations can be consistently defined and isolated across diverse LVLM architectures and tasks without significant overlap with other error types such as reasoning failures.","pith_extraction_headline":"Large vision-language models generate text that conflicts with input images, and this survey defines the problem while reviewing its symptoms, benchmarks, causes, and fixes."},"references":{"count":56,"sample":[{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"994f306f-a295-42db-934f-7f15ed59e399","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":2,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":null,"title":"Position-enhanced visual instruction tuning for multimodal large language models","work_id":"70a11f00-50ba-409c-b9da-619abaed18ea","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","work_id":"fb62cd1b-3991-40be-a987-3cfa5772b5b5","ref_index":4,"cited_arxiv_id":"2310.09478","is_internal_anchor":true},{"doi":"","year":null,"title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","work_id":"d9e035c7-9e23-4cc2-ad3e-be080fbbf2d9","ref_index":5,"cited_arxiv_id":"2312.14238","is_internal_anchor":true}],"resolved_work":56,"snapshot_sha256":"7ba873e9d79fbe63fdd9e6941ac8119a72ac6b9a9e74ca44ed6137c5a6884015","internal_anchors":21},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bfa4b190e5b5a0a408b1642f593f179644c4f57adb77771a6c7811986ef8d003"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.00253","created_at":"2026-05-18T04:33:37.170516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00253v2","created_at":"2026-05-18T04:33:37.170516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00253","created_at":"2026-05-18T04:33:37.170516+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCYNG54FMM74","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCYNG54FMM74BLAS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCYNG54F","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":44,"internal_anchor_count":44,"sample":[{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2503.02597","citing_title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09806","citing_title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16284","citing_title":"Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20965","citing_title":"Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20033","citing_title":"A Nash Equilibrium Framework For Training-Free Multimodal Step Verification","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01015","citing_title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2508.19652","citing_title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2509.15435","citing_title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2511.01458","citing_title":"When to Trust the Answer: Question-Aligned Semantic Nearest Neighbor Entropy for Safer Surgical VQA","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03992","citing_title":"Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05437","citing_title":"Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11824","citing_title":"Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18561","citing_title":"CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14403","citing_title":"DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27112","citing_title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02570","citing_title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11808","citing_title":"Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":194,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV","json":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV.json","graph_json":"https://pith.science/api/pith-number/MCYNG54FMM74BLASM5OMVQKGDV/graph.json","events_json":"https://pith.science/api/pith-number/MCYNG54FMM74BLASM5OMVQKGDV/events.json","paper":"https://pith.science/paper/MCYNG54F"},"agent_actions":{"view_html":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV","download_json":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV.json","view_paper":"https://pith.science/paper/MCYNG54F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00253&json=true","fetch_graph":"https://pith.science/api/pith-number/MCYNG54FMM74BLASM5OMVQKGDV/graph.json","fetch_events":"https://pith.science/api/pith-number/MCYNG54FMM74BLASM5OMVQKGDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV/action/storage_attestation","attest_author":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV/action/author_attestation","sign_citation":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV/action/citation_signature","submit_replication":"https://pith.science/pith/MCYNG54FMM74BLASM5OMVQKGDV/action/replication_record"}},"created_at":"2026-05-18T04:33:37.170516+00:00","updated_at":"2026-05-18T04:33:37.170516+00:00"}