{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XZIBOT557MKOZJU6F5YUB6ZIJX","short_pith_number":"pith:XZIBOT55","schema_version":"1.0","canonical_sha256":"be50174fbdfb14eca69e2f7140fb284df1bdbfe35aa2be1ab1dfcd1cc0db4383","source":{"kind":"arxiv","id":"2308.06394","version":3},"attestation_state":"computed","paper":{"title":"Detecting and Preventing Hallucinations in Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anisha Gunjal, Erhan Bas, Jihan Yin","submitted_at":"2023-08-11T21:35:20Z","abstract_excerpt":"Instruction tuned Large Vision Language Models (LVLMs) have significantly advanced in generalizing across a diverse set of multi-modal tasks, especially for Visual Question Answering (VQA). However, generating detailed responses that are visually grounded is still a challenging task for these models. We find that even the current state-of-the-art LVLMs (InstructBLIP) still contain a staggering 30 percent of the hallucinatory text in the form of non-existent objects, unfaithful descriptions, and inaccurate relationships. To address this, we introduce M-HalDetect, a (M)ultimodal (Hal)lucination "},"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":"2308.06394","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-11T21:35:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"30d3cbe548ca948264177c67e205fc127043e12d2efb3f65dae5a330f432b288","abstract_canon_sha256":"5eb01d13a10a7218153fa67929717676cf94eaa1f53df7107214220d78f79281"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:54.880432Z","signature_b64":"qlexFed2TGctVTXaucS1umkq7YphZIJfNIUxbEI2r6dMQS0DXjoMbxfGCpAQ4Nyh2ziPCpFBVIeYOoO//vbGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be50174fbdfb14eca69e2f7140fb284df1bdbfe35aa2be1ab1dfcd1cc0db4383","last_reissued_at":"2026-07-05T07:43:54.879995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:54.879995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting and Preventing Hallucinations in Large Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anisha Gunjal, Erhan Bas, Jihan Yin","submitted_at":"2023-08-11T21:35:20Z","abstract_excerpt":"Instruction tuned Large Vision Language Models (LVLMs) have significantly advanced in generalizing across a diverse set of multi-modal tasks, especially for Visual Question Answering (VQA). However, generating detailed responses that are visually grounded is still a challenging task for these models. We find that even the current state-of-the-art LVLMs (InstructBLIP) still contain a staggering 30 percent of the hallucinatory text in the form of non-existent objects, unfaithful descriptions, and inaccurate relationships. To address this, we introduce M-HalDetect, a (M)ultimodal (Hal)lucination "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06394","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/2308.06394/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":"2308.06394","created_at":"2026-07-05T07:43:54.880061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06394v3","created_at":"2026-07-05T07:43:54.880061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06394","created_at":"2026-07-05T07:43:54.880061+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZIBOT557MKO","created_at":"2026-07-05T07:43:54.880061+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZIBOT557MKOZJU6","created_at":"2026-07-05T07:43:54.880061+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZIBOT55","created_at":"2026-07-05T07:43:54.880061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15300","citing_title":"Deep Pre-Alignment for VLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2310.00754","citing_title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14566","citing_title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2309.05922","citing_title":"A Survey of Hallucination in Large Foundation Models","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07397","citing_title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":13,"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":112,"is_internal_anchor":false},{"citing_arxiv_id":"2309.01219","citing_title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26614","citing_title":"State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX","json":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX.json","graph_json":"https://pith.science/api/pith-number/XZIBOT557MKOZJU6F5YUB6ZIJX/graph.json","events_json":"https://pith.science/api/pith-number/XZIBOT557MKOZJU6F5YUB6ZIJX/events.json","paper":"https://pith.science/paper/XZIBOT55"},"agent_actions":{"view_html":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX","download_json":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX.json","view_paper":"https://pith.science/paper/XZIBOT55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06394&json=true","fetch_graph":"https://pith.science/api/pith-number/XZIBOT557MKOZJU6F5YUB6ZIJX/graph.json","fetch_events":"https://pith.science/api/pith-number/XZIBOT557MKOZJU6F5YUB6ZIJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX/action/storage_attestation","attest_author":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX/action/author_attestation","sign_citation":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX/action/citation_signature","submit_replication":"https://pith.science/pith/XZIBOT557MKOZJU6F5YUB6ZIJX/action/replication_record"}},"created_at":"2026-07-05T07:43:54.880061+00:00","updated_at":"2026-07-05T07:43:54.880061+00:00"}