{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2OR7NE4F7S45IVVO64SPQFGKTT","short_pith_number":"pith:2OR7NE4F","schema_version":"1.0","canonical_sha256":"d3a3f69385fcb9d456aef724f814ca9cf50cdceab9a17552c1c1b2f0a07e2e0d","source":{"kind":"arxiv","id":"2403.08319","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Conflicts for LLMs: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cunxiang Wang, Hongru Wang, Rongwu Xu, Wei Xu, Yue Zhang, Zehan Qi, Zhijiang Guo","submitted_at":"2024-03-13T08:02:23Z","abstract_excerpt":"This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and revi"},"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":"2403.08319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T08:02:23Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"ec87944015e4efc7e90b3d5d863fa22f54a2b411c3604819d43018034041f597","abstract_canon_sha256":"970df0d59a0eab4dbd4e36d3032944e1cd371d4ec45b0aef76228beb694d6664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:19.552540Z","signature_b64":"d3g+N11Wmd+Ck/ooTfvmtbhoWcJ2bWSQkTVEznZwOkTKlJDQ5Qbj7rHIVhcyBExVT9P5bRYK2GZmj69vUPeeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a3f69385fcb9d456aef724f814ca9cf50cdceab9a17552c1c1b2f0a07e2e0d","last_reissued_at":"2026-07-05T08:35:19.552064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:19.552064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Conflicts for LLMs: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cunxiang Wang, Hongru Wang, Rongwu Xu, Wei Xu, Yue Zhang, Zehan Qi, Zhijiang Guo","submitted_at":"2024-03-13T08:02:23Z","abstract_excerpt":"This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and revi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08319","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/2403.08319/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":"2403.08319","created_at":"2026-07-05T08:35:19.552118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08319v2","created_at":"2026-07-05T08:35:19.552118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08319","created_at":"2026-07-05T08:35:19.552118+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OR7NE4F7S45","created_at":"2026-07-05T08:35:19.552118+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OR7NE4F7S45IVVO","created_at":"2026-07-05T08:35:19.552118+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OR7NE4F","created_at":"2026-07-05T08:35:19.552118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11172","citing_title":"Predicting Future Behaviors in Reasoning Models Enables Better Steering","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07688","citing_title":"TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05403","citing_title":"Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26116","citing_title":"Divergent Recommendations, Convergent Diagnoses: Cross-Provider Failure-Mode Convergence in AI Commercial Recommendation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27786","citing_title":"SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27157","citing_title":"Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30207","citing_title":"Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25402","citing_title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22500","citing_title":"OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14172","citing_title":"Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11574","citing_title":"Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03255","citing_title":"Do LLMs have core beliefs?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23750","citing_title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07981","citing_title":"A Decomposition Perspective to Long-context Reasoning for LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15945","citing_title":"RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT","json":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT.json","graph_json":"https://pith.science/api/pith-number/2OR7NE4F7S45IVVO64SPQFGKTT/graph.json","events_json":"https://pith.science/api/pith-number/2OR7NE4F7S45IVVO64SPQFGKTT/events.json","paper":"https://pith.science/paper/2OR7NE4F"},"agent_actions":{"view_html":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT","download_json":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT.json","view_paper":"https://pith.science/paper/2OR7NE4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08319&json=true","fetch_graph":"https://pith.science/api/pith-number/2OR7NE4F7S45IVVO64SPQFGKTT/graph.json","fetch_events":"https://pith.science/api/pith-number/2OR7NE4F7S45IVVO64SPQFGKTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT/action/storage_attestation","attest_author":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT/action/author_attestation","sign_citation":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT/action/citation_signature","submit_replication":"https://pith.science/pith/2OR7NE4F7S45IVVO64SPQFGKTT/action/replication_record"}},"created_at":"2026-07-05T08:35:19.552118+00:00","updated_at":"2026-07-05T08:35:19.552118+00:00"}