{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:42L6UZYCVNIUNKNQDSCGJDBIX7","short_pith_number":"pith:42L6UZYC","schema_version":"1.0","canonical_sha256":"e697ea6702ab5146a9b01c84648c28bfdae2f81d7374af22d597b6b5da9182ba","source":{"kind":"arxiv","id":"2506.11073","version":1},"attestation_state":"computed","paper":{"title":"CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baohang Li, Bing Qin, Dandan Tu, Duyu Tang, Kui Jiang, Libo Qin, Qiming Li, Xiaocheng Feng, Yang Xiang, Yichong Huang, Yunfei Lu, Zekai Ye, Zhirui Zhang","submitted_at":"2025-06-03T11:17:16Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing queries in non-English languages compared to English. Most existing approaches to address these rely on pretraining or fine-tuning, which are resource-intensive. In this paper, inspired by observing the disparities in cross-modal attention patterns across languages, we propose Cross-Lingual Attention Intervention for Mitigating multilingual object hallucina"},"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":"2506.11073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T11:17:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2e1958b196ac44589cd2352a7911efdff3a5eca383670396b6e8908f49d6ad7d","abstract_canon_sha256":"baec297d2c7707fe2b3879f8244ef90d867954c37306ef0a688539e1caf392f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.052651Z","signature_b64":"pksGAnUxDRQky/87aTryOUdW+wESEL3m0o0JNqmag83NQh1g112iVTxv4ZbpzzGYCoGy/kiQtFonin+SIpEODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e697ea6702ab5146a9b01c84648c28bfdae2f81d7374af22d597b6b5da9182ba","last_reissued_at":"2026-07-05T11:20:59.052021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.052021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baohang Li, Bing Qin, Dandan Tu, Duyu Tang, Kui Jiang, Libo Qin, Qiming Li, Xiaocheng Feng, Yang Xiang, Yichong Huang, Yunfei Lu, Zekai Ye, Zhirui Zhang","submitted_at":"2025-06-03T11:17:16Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing queries in non-English languages compared to English. Most existing approaches to address these rely on pretraining or fine-tuning, which are resource-intensive. In this paper, inspired by observing the disparities in cross-modal attention patterns across languages, we propose Cross-Lingual Attention Intervention for Mitigating multilingual object hallucina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11073","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/2506.11073/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":"2506.11073","created_at":"2026-07-05T11:20:59.052089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11073v1","created_at":"2026-07-05T11:20:59.052089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11073","created_at":"2026-07-05T11:20:59.052089+00:00"},{"alias_kind":"pith_short_12","alias_value":"42L6UZYCVNIU","created_at":"2026-07-05T11:20:59.052089+00:00"},{"alias_kind":"pith_short_16","alias_value":"42L6UZYCVNIUNKNQ","created_at":"2026-07-05T11:20:59.052089+00:00"},{"alias_kind":"pith_short_8","alias_value":"42L6UZYC","created_at":"2026-07-05T11:20:59.052089+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/42L6UZYCVNIUNKNQDSCGJDBIX7","json":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7.json","graph_json":"https://pith.science/api/pith-number/42L6UZYCVNIUNKNQDSCGJDBIX7/graph.json","events_json":"https://pith.science/api/pith-number/42L6UZYCVNIUNKNQDSCGJDBIX7/events.json","paper":"https://pith.science/paper/42L6UZYC"},"agent_actions":{"view_html":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7","download_json":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7.json","view_paper":"https://pith.science/paper/42L6UZYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11073&json=true","fetch_graph":"https://pith.science/api/pith-number/42L6UZYCVNIUNKNQDSCGJDBIX7/graph.json","fetch_events":"https://pith.science/api/pith-number/42L6UZYCVNIUNKNQDSCGJDBIX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7/action/storage_attestation","attest_author":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7/action/author_attestation","sign_citation":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7/action/citation_signature","submit_replication":"https://pith.science/pith/42L6UZYCVNIUNKNQDSCGJDBIX7/action/replication_record"}},"created_at":"2026-07-05T11:20:59.052089+00:00","updated_at":"2026-07-05T11:20:59.052089+00:00"}