{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EROKCBY3KLZOQXCY4EPS4KZA5I","short_pith_number":"pith:EROKCBY3","schema_version":"1.0","canonical_sha256":"245ca1071b52f2e85c58e11f2e2b20ea1889993deecc0d448bfacef49546fe85","source":{"kind":"arxiv","id":"2311.17911","version":3},"attestation_state":"computed","paper":{"title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang, Nenghai Yu, Pan Zhang, Qidong Huang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2023-11-29T18:57:07Z","abstract_excerpt":"Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with specific designed data or inferencing with external knowledge from other sources, incurring inevitable additional costs. In this paper, we present OPERA, a novel MLLM decoding method grounded in an Over-trust Penalty and a Retrospection-Allocation strategy, serving as a nearly free lunch to alleviate the hallucination issue without additional data, knowledge, or "},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.17911","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T18:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"24af889259c81d6398a09a73161e09f6e3091d58a9dde2a38899ba1f9d822871","abstract_canon_sha256":"a421b1673c43e8cec747c528f8bc07c79b38649dcc2377668fee6fcc6dbc8d2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:53.316261Z","signature_b64":"RLJHOT9rhnb9cPzv8cEYfMe96Dn3++39a3V/2mg7grSJEgmKutV1k8R2EZPNo4HSKJtRimHKGH6GiUiI345MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"245ca1071b52f2e85c58e11f2e2b20ea1889993deecc0d448bfacef49546fe85","last_reissued_at":"2026-07-05T07:54:53.315772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:53.315772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang, Nenghai Yu, Pan Zhang, Qidong Huang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2023-11-29T18:57:07Z","abstract_excerpt":"Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with specific designed data or inferencing with external knowledge from other sources, incurring inevitable additional costs. In this paper, we present OPERA, a novel MLLM decoding method grounded in an Over-trust Penalty and a Retrospection-Allocation strategy, serving as a nearly free lunch to alleviate the hallucination issue without additional data, knowledge, or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17911","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.17911/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2311.17911","created_at":"2026-07-05T07:54:53.315835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17911v3","created_at":"2026-07-05T07:54:53.315835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17911","created_at":"2026-07-05T07:54:53.315835+00:00"},{"alias_kind":"pith_short_12","alias_value":"EROKCBY3KLZO","created_at":"2026-07-05T07:54:53.315835+00:00"},{"alias_kind":"pith_short_16","alias_value":"EROKCBY3KLZOQXCY","created_at":"2026-07-05T07:54:53.315835+00:00"},{"alias_kind":"pith_short_8","alias_value":"EROKCBY3","created_at":"2026-07-05T07:54:53.315835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27993","citing_title":"Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2402.11411","citing_title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","ref_index":153,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I","json":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I.json","graph_json":"https://pith.science/api/pith-number/EROKCBY3KLZOQXCY4EPS4KZA5I/graph.json","events_json":"https://pith.science/api/pith-number/EROKCBY3KLZOQXCY4EPS4KZA5I/events.json","paper":"https://pith.science/paper/EROKCBY3"},"agent_actions":{"view_html":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I","download_json":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I.json","view_paper":"https://pith.science/paper/EROKCBY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17911&json=true","fetch_graph":"https://pith.science/api/pith-number/EROKCBY3KLZOQXCY4EPS4KZA5I/graph.json","fetch_events":"https://pith.science/api/pith-number/EROKCBY3KLZOQXCY4EPS4KZA5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I/action/storage_attestation","attest_author":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I/action/author_attestation","sign_citation":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I/action/citation_signature","submit_replication":"https://pith.science/pith/EROKCBY3KLZOQXCY4EPS4KZA5I/action/replication_record"}},"created_at":"2026-07-05T07:54:53.315835+00:00","updated_at":"2026-07-05T07:54:53.315835+00:00"}