{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CGWCRQHWRBTD6BHOFVDS4SNZQR","short_pith_number":"pith:CGWCRQHW","schema_version":"1.0","canonical_sha256":"11ac28c0f688663f04ee2d472e49b98471b9cab6d846467018d116b8883772fa","source":{"kind":"arxiv","id":"2408.00555","version":1},"attestation_state":"computed","paper":{"title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianfeng Dong, Jishuo Sun, Qiyuan Chen, Wei Wei, Xiaoye Qu","submitted_at":"2024-08-01T13:38:58Z","abstract_excerpt":"Despite the remarkable ability of large vision-language models (LVLMs) in image comprehension, these models frequently generate plausible yet factually incorrect responses, a phenomenon known as hallucination.Recently, in large language models (LLMs), augmenting LLMs by retrieving information from external knowledge resources has been proven as a promising solution to mitigate hallucinations.However, the retrieval augmentation in LVLM significantly lags behind the widespread applications of LVLM. Moreover, when transferred to augmenting LVLMs, sometimes the hallucination degree of the model is"},"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":"2408.00555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T13:38:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f65a4269a979fbf4253fa9018be8cb7b7da8944f2e616b8bf2b92c5bb3414c68","abstract_canon_sha256":"052400627b57c0ed453767cf842f2c4adcb0b6449ac6c515f831a99402b6eb94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:05.590550Z","signature_b64":"jydqt5q9Yjn2Wg32PN8D3RjiGCJj8Ej+n2XWDxKKXyORGwwN/DwhbnJW82RtiM5yhQt4PpQFATkqomFvIpcFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ac28c0f688663f04ee2d472e49b98471b9cab6d846467018d116b8883772fa","last_reissued_at":"2026-07-05T08:51:05.590078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:05.590078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianfeng Dong, Jishuo Sun, Qiyuan Chen, Wei Wei, Xiaoye Qu","submitted_at":"2024-08-01T13:38:58Z","abstract_excerpt":"Despite the remarkable ability of large vision-language models (LVLMs) in image comprehension, these models frequently generate plausible yet factually incorrect responses, a phenomenon known as hallucination.Recently, in large language models (LLMs), augmenting LLMs by retrieving information from external knowledge resources has been proven as a promising solution to mitigate hallucinations.However, the retrieval augmentation in LVLM significantly lags behind the widespread applications of LVLM. Moreover, when transferred to augmenting LVLMs, sometimes the hallucination degree of the model is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00555","kind":"arxiv","version":1},"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/2408.00555/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":"2408.00555","created_at":"2026-07-05T08:51:05.590136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00555v1","created_at":"2026-07-05T08:51:05.590136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00555","created_at":"2026-07-05T08:51:05.590136+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGWCRQHWRBTD","created_at":"2026-07-05T08:51:05.590136+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGWCRQHWRBTD6BHO","created_at":"2026-07-05T08:51:05.590136+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGWCRQHW","created_at":"2026-07-05T08:51:05.590136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11559","citing_title":"When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":261,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR","json":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR.json","graph_json":"https://pith.science/api/pith-number/CGWCRQHWRBTD6BHOFVDS4SNZQR/graph.json","events_json":"https://pith.science/api/pith-number/CGWCRQHWRBTD6BHOFVDS4SNZQR/events.json","paper":"https://pith.science/paper/CGWCRQHW"},"agent_actions":{"view_html":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR","download_json":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR.json","view_paper":"https://pith.science/paper/CGWCRQHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00555&json=true","fetch_graph":"https://pith.science/api/pith-number/CGWCRQHWRBTD6BHOFVDS4SNZQR/graph.json","fetch_events":"https://pith.science/api/pith-number/CGWCRQHWRBTD6BHOFVDS4SNZQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR/action/storage_attestation","attest_author":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR/action/author_attestation","sign_citation":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR/action/citation_signature","submit_replication":"https://pith.science/pith/CGWCRQHWRBTD6BHOFVDS4SNZQR/action/replication_record"}},"created_at":"2026-07-05T08:51:05.590136+00:00","updated_at":"2026-07-05T08:51:05.590136+00:00"}