{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WISR7F3GZLFOAVJUUYVBGV52BA","short_pith_number":"pith:WISR7F3G","schema_version":"1.0","canonical_sha256":"b2251f9766cacae05534a62a1357ba083f080e0a1ad526cb1e177947b8b915b3","source":{"kind":"arxiv","id":"2402.18476","version":1},"attestation_state":"computed","paper":{"title":"IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Jieping Ye, Jun Liu, Lanyun Zhu, Peng Xu, Tianrun Chen","submitted_at":"2024-02-28T16:57:22Z","abstract_excerpt":"Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations. An over-reliance on linguistic priors has been identified as a key factor leading to these hallucinations. In this paper, we propose to alleviate this problem by introducing a novel image-biased decoding (IBD) technique. Our method derives the next-token probability distribution by contrasting predictions from a conventional LVLM with those of an image-biased LVLM, thereby amplifying the correct information highly "},"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":"2402.18476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T16:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"6c7f826fbcab5008c2496d12c0dc30710a6fcb9c8911d98aae90cd90b8789d6c","abstract_canon_sha256":"9a54aa1e927da7f85fb99a052c1eb5468d6fa79ff72af7650638205b77393fe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:16.567089Z","signature_b64":"wfLoeDlaA0v4l2JYu/13oFFiIFZgaGZgWWxJYSzDsypPhPKN2cZpepnvFC4eWC/AQmVkbZf34e+ek7VeQC7sBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2251f9766cacae05534a62a1357ba083f080e0a1ad526cb1e177947b8b915b3","last_reissued_at":"2026-07-05T07:50:16.566655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:16.566655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Jieping Ye, Jun Liu, Lanyun Zhu, Peng Xu, Tianrun Chen","submitted_at":"2024-02-28T16:57:22Z","abstract_excerpt":"Despite achieving rapid developments and with widespread applications, Large Vision-Language Models (LVLMs) confront a serious challenge of being prone to generating hallucinations. An over-reliance on linguistic priors has been identified as a key factor leading to these hallucinations. In this paper, we propose to alleviate this problem by introducing a novel image-biased decoding (IBD) technique. Our method derives the next-token probability distribution by contrasting predictions from a conventional LVLM with those of an image-biased LVLM, thereby amplifying the correct information highly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18476","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/2402.18476/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":"2402.18476","created_at":"2026-07-05T07:50:16.566712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18476v1","created_at":"2026-07-05T07:50:16.566712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18476","created_at":"2026-07-05T07:50:16.566712+00:00"},{"alias_kind":"pith_short_12","alias_value":"WISR7F3GZLFO","created_at":"2026-07-05T07:50:16.566712+00:00"},{"alias_kind":"pith_short_16","alias_value":"WISR7F3GZLFOAVJU","created_at":"2026-07-05T07:50:16.566712+00:00"},{"alias_kind":"pith_short_8","alias_value":"WISR7F3G","created_at":"2026-07-05T07:50:16.566712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15300","citing_title":"Deep Pre-Alignment for VLMs","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":273,"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":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02200","citing_title":"ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA","json":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA.json","graph_json":"https://pith.science/api/pith-number/WISR7F3GZLFOAVJUUYVBGV52BA/graph.json","events_json":"https://pith.science/api/pith-number/WISR7F3GZLFOAVJUUYVBGV52BA/events.json","paper":"https://pith.science/paper/WISR7F3G"},"agent_actions":{"view_html":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA","download_json":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA.json","view_paper":"https://pith.science/paper/WISR7F3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18476&json=true","fetch_graph":"https://pith.science/api/pith-number/WISR7F3GZLFOAVJUUYVBGV52BA/graph.json","fetch_events":"https://pith.science/api/pith-number/WISR7F3GZLFOAVJUUYVBGV52BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA/action/storage_attestation","attest_author":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA/action/author_attestation","sign_citation":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA/action/citation_signature","submit_replication":"https://pith.science/pith/WISR7F3GZLFOAVJUUYVBGV52BA/action/replication_record"}},"created_at":"2026-07-05T07:50:16.566712+00:00","updated_at":"2026-07-05T07:50:16.566712+00:00"}