{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYNXX2D3BBZ7N5IJCMATS754SI","short_pith_number":"pith:HYNXX2D3","schema_version":"1.0","canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","source":{"kind":"arxiv","id":"2407.21771","version":1},"attestation_state":"computed","paper":{"title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kecheng Zheng, Shi Liu, Wei Chen","submitted_at":"2024-07-31T17:46:57Z","abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder and language model may led to LLMs assuming a predominant role in multi-modal comprehension. This imbalance in LVLMs may result in the instances of hallucinatory. Concretely, LVLMs may generate consistent descriptions with or without visual input, indicating that certain outputs are influenced solely by context text. We refer to this phenomenon as \"text inerti"},"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":"2407.21771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T17:46:57Z","cross_cats_sorted":[],"title_canon_sha256":"8a823ed20d3b9ff79b6e55191fd42bba4c869c136e360d7e0cf93ca41e964f99","abstract_canon_sha256":"538ad52543425a342aea7fdc4f86d538aa93c8a656dcaa6d767690e9898c9336"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:43.379911Z","signature_b64":"dbL2GKlXRlQy55noYrMNoidjF1cmmY7IPduUXGOOUH6hokXsAwSfaDc9JjicvmoK/svzCtPBCuQk9h0jKATlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e1b7be87b0873f6f5091301397fbc920ab580a687ad87eefc3752388a619a12","last_reissued_at":"2026-07-05T08:50:43.379569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:43.379569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kecheng Zheng, Shi Liu, Wei Chen","submitted_at":"2024-07-31T17:46:57Z","abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder and language model may led to LLMs assuming a predominant role in multi-modal comprehension. This imbalance in LVLMs may result in the instances of hallucinatory. Concretely, LVLMs may generate consistent descriptions with or without visual input, indicating that certain outputs are influenced solely by context text. We refer to this phenomenon as \"text inerti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21771","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/2407.21771/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":"2407.21771","created_at":"2026-07-05T08:50:43.379625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21771v1","created_at":"2026-07-05T08:50:43.379625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21771","created_at":"2026-07-05T08:50:43.379625+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYNXX2D3BBZ7","created_at":"2026-07-05T08:50:43.379625+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYNXX2D3BBZ7N5IJ","created_at":"2026-07-05T08:50:43.379625+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYNXX2D3","created_at":"2026-07-05T08:50:43.379625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17417","citing_title":"A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10292","citing_title":"Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21472","citing_title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21911","citing_title":"When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI","json":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI.json","graph_json":"https://pith.science/api/pith-number/HYNXX2D3BBZ7N5IJCMATS754SI/graph.json","events_json":"https://pith.science/api/pith-number/HYNXX2D3BBZ7N5IJCMATS754SI/events.json","paper":"https://pith.science/paper/HYNXX2D3"},"agent_actions":{"view_html":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI","download_json":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI.json","view_paper":"https://pith.science/paper/HYNXX2D3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21771&json=true","fetch_graph":"https://pith.science/api/pith-number/HYNXX2D3BBZ7N5IJCMATS754SI/graph.json","fetch_events":"https://pith.science/api/pith-number/HYNXX2D3BBZ7N5IJCMATS754SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/action/storage_attestation","attest_author":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/action/author_attestation","sign_citation":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/action/citation_signature","submit_replication":"https://pith.science/pith/HYNXX2D3BBZ7N5IJCMATS754SI/action/replication_record"}},"created_at":"2026-07-05T08:50:43.379625+00:00","updated_at":"2026-07-05T08:50:43.379625+00:00"}