{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LHCFKVJWISIVCBV5NA7MDYOMDV","short_pith_number":"pith:LHCFKVJW","schema_version":"1.0","canonical_sha256":"59c455553644915106bd683ec1e1cc1d7d3389ca561162304a99b6c4f90a7930","source":{"kind":"arxiv","id":"2506.07184","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Di Wang, Guimin Hu, Junchi Yao, Liangliang You, Lijie Hu, Shu Yang","submitted_at":"2025-06-08T15:08:52Z","abstract_excerpt":"While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Se"},"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":"2506.07184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T15:08:52Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"85c0f4e6e68e92572dd9fb495f75ad317964bda0782e70a5ce26ef7ea729694b","abstract_canon_sha256":"27c4421490626a4366483b5dadfcb226024a83b2ebc00fe041d559e865c9f1d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:03.148240Z","signature_b64":"t3u9Iaf5F42gG/wGEwMl00sLMHitbpjEGB4C/gRTRRFeZs+eG9lCDJPi//cQJAf+6AxoiIX3mXN499sA96XqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59c455553644915106bd683ec1e1cc1d7d3389ca561162304a99b6c4f90a7930","last_reissued_at":"2026-07-05T11:18:03.147702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:03.147702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Di Wang, Guimin Hu, Junchi Yao, Liangliang You, Lijie Hu, Shu Yang","submitted_at":"2025-06-08T15:08:52Z","abstract_excerpt":"While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07184","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/2506.07184/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":"2506.07184","created_at":"2026-07-05T11:18:03.147775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07184v1","created_at":"2026-07-05T11:18:03.147775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07184","created_at":"2026-07-05T11:18:03.147775+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHCFKVJWISIV","created_at":"2026-07-05T11:18:03.147775+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHCFKVJWISIVCBV5","created_at":"2026-07-05T11:18:03.147775+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHCFKVJW","created_at":"2026-07-05T11:18:03.147775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV","json":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV.json","graph_json":"https://pith.science/api/pith-number/LHCFKVJWISIVCBV5NA7MDYOMDV/graph.json","events_json":"https://pith.science/api/pith-number/LHCFKVJWISIVCBV5NA7MDYOMDV/events.json","paper":"https://pith.science/paper/LHCFKVJW"},"agent_actions":{"view_html":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV","download_json":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV.json","view_paper":"https://pith.science/paper/LHCFKVJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07184&json=true","fetch_graph":"https://pith.science/api/pith-number/LHCFKVJWISIVCBV5NA7MDYOMDV/graph.json","fetch_events":"https://pith.science/api/pith-number/LHCFKVJWISIVCBV5NA7MDYOMDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV/action/storage_attestation","attest_author":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV/action/author_attestation","sign_citation":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV/action/citation_signature","submit_replication":"https://pith.science/pith/LHCFKVJWISIVCBV5NA7MDYOMDV/action/replication_record"}},"created_at":"2026-07-05T11:18:03.147775+00:00","updated_at":"2026-07-05T11:18:03.147775+00:00"}