{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2GF6IRMQVNJ752LFL76TB2M2TP","short_pith_number":"pith:2GF6IRMQ","schema_version":"1.0","canonical_sha256":"d18be44590ab53fee9655ffd30e99a9bce33e616517064ed81f3e91c4ee343e5","source":{"kind":"arxiv","id":"2402.08680","version":2},"attestation_state":"computed","paper":{"title":"Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Linxi Zhao, Quanquan Gu, Weitong Zhang, Yihe Deng","submitted_at":"2024-02-13T18:59:05Z","abstract_excerpt":"The advancement of Large Vision-Language Models (LVLMs) has increasingly highlighted the critical issue of their tendency to hallucinate non-existing objects in the images. To address this issue, previous works focused on using specially curated datasets or powerful LLMs to rectify the outputs of LVLMs. However, these approaches require either costly training or fine-tuning, or API access to proprietary LLMs for post-generation correction. In response to these limitations, we propose Mitigating hallucinAtion via image-gRounded guIdaNcE (MARINE), a framework that is both training-free and API-f"},"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":"2402.08680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:59:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"47a90e0dea4b9ad3e1c2eda8104aadebfaf6f2a38a130cabc91b587be8b5f418","abstract_canon_sha256":"9f730fb8f83cff7b9bc82cdbc8ea03265fc29d8c2d951f77ee1b39981f79071f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:02.593783Z","signature_b64":"td1F7w7dHi17lyx2tuejNWCOp/4yHyU3yp0VGIK8sDDuxJa8O5VfNkeAnjaBCkOxYXeteF5BqJqp/n3ZiOY6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d18be44590ab53fee9655ffd30e99a9bce33e616517064ed81f3e91c4ee343e5","last_reissued_at":"2026-07-05T11:20:02.593271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:02.593271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Linxi Zhao, Quanquan Gu, Weitong Zhang, Yihe Deng","submitted_at":"2024-02-13T18:59:05Z","abstract_excerpt":"The advancement of Large Vision-Language Models (LVLMs) has increasingly highlighted the critical issue of their tendency to hallucinate non-existing objects in the images. To address this issue, previous works focused on using specially curated datasets or powerful LLMs to rectify the outputs of LVLMs. However, these approaches require either costly training or fine-tuning, or API access to proprietary LLMs for post-generation correction. In response to these limitations, we propose Mitigating hallucinAtion via image-gRounded guIdaNcE (MARINE), a framework that is both training-free and API-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08680","kind":"arxiv","version":2},"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/2402.08680/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":"2402.08680","created_at":"2026-07-05T11:20:02.593343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08680v2","created_at":"2026-07-05T11:20:02.593343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08680","created_at":"2026-07-05T11:20:02.593343+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GF6IRMQVNJ7","created_at":"2026-07-05T11:20:02.593343+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GF6IRMQVNJ752LF","created_at":"2026-07-05T11:20:02.593343+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GF6IRMQ","created_at":"2026-07-05T11:20:02.593343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24957","citing_title":"Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30911","citing_title":"What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15300","citing_title":"Deep Pre-Alignment for VLMs","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10676","citing_title":"Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10622","citing_title":"Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04874","citing_title":"Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":217,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12115","citing_title":"HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":293,"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":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP","json":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP.json","graph_json":"https://pith.science/api/pith-number/2GF6IRMQVNJ752LFL76TB2M2TP/graph.json","events_json":"https://pith.science/api/pith-number/2GF6IRMQVNJ752LFL76TB2M2TP/events.json","paper":"https://pith.science/paper/2GF6IRMQ"},"agent_actions":{"view_html":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP","download_json":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP.json","view_paper":"https://pith.science/paper/2GF6IRMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08680&json=true","fetch_graph":"https://pith.science/api/pith-number/2GF6IRMQVNJ752LFL76TB2M2TP/graph.json","fetch_events":"https://pith.science/api/pith-number/2GF6IRMQVNJ752LFL76TB2M2TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP/action/storage_attestation","attest_author":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP/action/author_attestation","sign_citation":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP/action/citation_signature","submit_replication":"https://pith.science/pith/2GF6IRMQVNJ752LFL76TB2M2TP/action/replication_record"}},"created_at":"2026-07-05T11:20:02.593343+00:00","updated_at":"2026-07-05T11:20:02.593343+00:00"}