{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2CC62ETSO5IOGBPTRWZ4EQRIIQ","short_pith_number":"pith:2CC62ETS","schema_version":"1.0","canonical_sha256":"d085ed12727750e305f38db3c2422844117bbc33a4caee2b605a4ef71814d040","source":{"kind":"arxiv","id":"2310.14566","version":5},"attestation_state":"computed","paper":{"title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HallusionBench shows even GPT-4V reaches only 31.42 percent accuracy on paired questions that expose language hallucination and visual illusion in vision-language models.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Furong Huang, Fuxiao Liu, Lichang Chen, Ruiqi Xian, Tianrui Guan, Tianyi Zhou, Xiaoyu Liu, Xijun Wang, Xiyang Wu, Yaser Yacoob, Zongxia Li","submitted_at":"2023-10-23T04:49:09Z","abstract_excerpt":"We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitativ"},"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":"2310.14566","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T04:49:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"209a053a5e9fb6f85c51f383c22f0271269e5bf11b4b94c005535fb95ebeeca0","abstract_canon_sha256":"75c5e52bb5f0a30f0f41eb1817f924d839d8a4359caf019c8aa79d5814b85e4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:45.996231Z","signature_b64":"Mux6NtEBTf8U7p10xPc2WABdNekgEqwuiK4iYc/9stWFjMGU8YiM4NAZIlMvk6d9gUG4viHje2mu5I7aIWEDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d085ed12727750e305f38db3c2422844117bbc33a4caee2b605a4ef71814d040","last_reissued_at":"2026-05-17T23:38:45.995639Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:45.995639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HallusionBench shows even GPT-4V reaches only 31.42 percent accuracy on paired questions that expose language hallucination and visual illusion in vision-language models.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Furong Huang, Fuxiao Liu, Lichang Chen, Ruiqi Xian, Tianrui Guan, Tianyi Zhou, Xiaoyu Liu, Xijun Wang, Xiyang Wu, Yaser Yacoob, Zongxia Li","submitted_at":"2023-10-23T04:49:09Z","abstract_excerpt":"We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitativ"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that human-expert-crafted questions with the novel control-group structure accurately isolate and measure entangled language hallucination and visual illusion without introducing confounding biases or subjective interpretations in scoring.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HallusionBench shows even GPT-4V reaches only 31.42 percent accuracy on paired questions that expose language hallucination and visual illusion in vision-language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"455c88252001f05f636a22d2716650fa8f0fadc62c9c6be0eed86db7df2cff9c"},"source":{"id":"2310.14566","kind":"arxiv","version":5},"verdict":{"id":"320843f4-2d58-4ce0-9b75-93564f84ba77","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T01:17:20.225173Z","strongest_claim":"In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%.","one_line_summary":"HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that human-expert-crafted questions with the novel control-group structure accurately isolate and measure entangled language hallucination and visual illusion without introducing confounding biases or subjective interpretations in scoring.","pith_extraction_headline":"HallusionBench shows even GPT-4V reaches only 31.42 percent accuracy on paired questions that expose language hallucination and visual illusion in vision-language models."},"references":{"count":63,"sample":[{"doi":"","year":2023,"title":"Gpt-4v(ision) system card. 2023. 6, 7","work_id":"88a556c3-5f22-4f71-b403-084ceddb10a2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"nocaps: novel object captioning at scale","work_id":"cf1f8da2-1488-4dd0-8a72-2412fb7c436d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Flamingo: a visual language model for few-shot learning","work_id":"31e3af5c-9fec-43d9-b533-5bb70172dd15","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Vqa: Visual question answering","work_id":"3db513bc-ec97-47d1-bc83-6eb38b02a2d9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Anas Awadalla, Irena Gao, Joshua Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bit- ton, Samir Gadre, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell","work_id":"585147a1-ddd5-4f10-93ea-dae26c9319b1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":63,"snapshot_sha256":"bbbaaf3be139cf261d8684897cdc7b95496f55bbf49eaea24af242076ee8cc1c","internal_anchors":22},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3fa34980d59bf013942a12d97745133ef222683d99a4935b8c7c25f09303061e"},"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":"2310.14566","created_at":"2026-05-17T23:38:45.995736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14566v5","created_at":"2026-05-17T23:38:45.995736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14566","created_at":"2026-05-17T23:38:45.995736+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CC62ETSO5IO","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CC62ETSO5IOGBPT","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CC62ETS","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2502.13923","citing_title":"Qwen2.5-VL Technical Report","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19250","citing_title":"Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20164","citing_title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2505.21472","citing_title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13868","citing_title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2511.21678","citing_title":"Agentic Learner with Grow-and-Refine Multimodal Semantic Memory","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03438","citing_title":"Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2406.09411","citing_title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12623","citing_title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2503.12937","citing_title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2311.07397","citing_title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13310","citing_title":"Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.18373","citing_title":"To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13156","citing_title":"Dual-Pathway Circuits of Object Hallucination in Vision-Language Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2306.14565","citing_title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2409.02813","citing_title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","ref_index":28,"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":191,"is_internal_anchor":true},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10219","citing_title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ","json":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ.json","graph_json":"https://pith.science/api/pith-number/2CC62ETSO5IOGBPTRWZ4EQRIIQ/graph.json","events_json":"https://pith.science/api/pith-number/2CC62ETSO5IOGBPTRWZ4EQRIIQ/events.json","paper":"https://pith.science/paper/2CC62ETS"},"agent_actions":{"view_html":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ","download_json":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ.json","view_paper":"https://pith.science/paper/2CC62ETS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14566&json=true","fetch_graph":"https://pith.science/api/pith-number/2CC62ETSO5IOGBPTRWZ4EQRIIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2CC62ETSO5IOGBPTRWZ4EQRIIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ/action/storage_attestation","attest_author":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ/action/author_attestation","sign_citation":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ/action/citation_signature","submit_replication":"https://pith.science/pith/2CC62ETSO5IOGBPTRWZ4EQRIIQ/action/replication_record"}},"created_at":"2026-05-17T23:38:45.995736+00:00","updated_at":"2026-05-17T23:38:45.995736+00:00"}