{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7BNYFED63FE4FXNE2BKBNQ3AAO","short_pith_number":"pith:7BNYFED6","schema_version":"1.0","canonical_sha256":"f85b82907ed949c2dda4d05416c360038484130c8e0c4bf843647033216b05a1","source":{"kind":"arxiv","id":"2311.07362","version":4},"attestation_state":"computed","paper":{"title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Minjoon Seo, Seongyun Lee, Sue Hyun Park, Yongrae Jo","submitted_at":"2023-11-13T14:26:24Z","abstract_excerpt":"Large multimodal models suffer from multimodal hallucination, where they provide incorrect responses misaligned with the given visual information. Recent works have conjectured that one of the reasons behind multimodal hallucination is due to the vision encoder failing to ground on the image properly. To mitigate this issue, we propose a novel approach that leverages self-feedback as visual cues. Building on this approach, we introduce Volcano, a multimodal self-feedback guided revision model. Volcano generates natural language feedback to its initial response based on the provided visual info"},"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":"2311.07362","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T14:26:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"49c428c105e2be7cc991318e7811b61e832582775ac1dbc7daade6e61cb0feaa","abstract_canon_sha256":"f7030cb51d2df14c36d3c1bfe58401f391b83882082890dbb2190b52707c3f43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:08.281499Z","signature_b64":"JsQz0Bldlfse34OQ29ROmGlFlxH7q3cG3fgbCe+/Mh2tmTpL8oggaWs213ON5T1iE1KC8A8KXZO4J25WyqYRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85b82907ed949c2dda4d05416c360038484130c8e0c4bf843647033216b05a1","last_reissued_at":"2026-07-05T08:03:08.280749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:08.280749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Minjoon Seo, Seongyun Lee, Sue Hyun Park, Yongrae Jo","submitted_at":"2023-11-13T14:26:24Z","abstract_excerpt":"Large multimodal models suffer from multimodal hallucination, where they provide incorrect responses misaligned with the given visual information. Recent works have conjectured that one of the reasons behind multimodal hallucination is due to the vision encoder failing to ground on the image properly. To mitigate this issue, we propose a novel approach that leverages self-feedback as visual cues. Building on this approach, we introduce Volcano, a multimodal self-feedback guided revision model. Volcano generates natural language feedback to its initial response based on the provided visual info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07362","kind":"arxiv","version":4},"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/2311.07362/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":"2311.07362","created_at":"2026-07-05T08:03:08.280845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07362v4","created_at":"2026-07-05T08:03:08.280845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07362","created_at":"2026-07-05T08:03:08.280845+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BNYFED63FE4","created_at":"2026-07-05T08:03:08.280845+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BNYFED63FE4FXNE","created_at":"2026-07-05T08:03:08.280845+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BNYFED6","created_at":"2026-07-05T08:03:08.280845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17982","citing_title":"Mitigating Multimodal Hallucination via Phase-wise Self-reward","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04641","citing_title":"CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO","json":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO.json","graph_json":"https://pith.science/api/pith-number/7BNYFED63FE4FXNE2BKBNQ3AAO/graph.json","events_json":"https://pith.science/api/pith-number/7BNYFED63FE4FXNE2BKBNQ3AAO/events.json","paper":"https://pith.science/paper/7BNYFED6"},"agent_actions":{"view_html":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO","download_json":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO.json","view_paper":"https://pith.science/paper/7BNYFED6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07362&json=true","fetch_graph":"https://pith.science/api/pith-number/7BNYFED63FE4FXNE2BKBNQ3AAO/graph.json","fetch_events":"https://pith.science/api/pith-number/7BNYFED63FE4FXNE2BKBNQ3AAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO/action/storage_attestation","attest_author":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO/action/author_attestation","sign_citation":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO/action/citation_signature","submit_replication":"https://pith.science/pith/7BNYFED63FE4FXNE2BKBNQ3AAO/action/replication_record"}},"created_at":"2026-07-05T08:03:08.280845+00:00","updated_at":"2026-07-05T08:03:08.280845+00:00"}