{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZGGOVILZSNCDRKDSYCFHFPERTU","short_pith_number":"pith:ZGGOVILZ","schema_version":"1.0","canonical_sha256":"c98ceaa179934438a872c08a72bc919d1b2836b884baa054aad4e56f6b09c50e","source":{"kind":"arxiv","id":"2408.12076","version":1},"attestation_state":"computed","paper":{"title":"ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiashuo Sun, Juntao Li, Jun Zhang, Min Zhang, Tong Zhu, Xiaoye Qu, Yanshu Li, Yu Cheng, Zhaochen Su","submitted_at":"2024-08-22T02:33:13Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the conflicts between the inherent knowledge of LLMs and the retrieved contextual knowledge. However, a thorough assessment of knowledge conflict in LLMs is still missing. Motivated by this research gap, we present ConflictBank, the first comprehensive benchmark developed to systematically evaluate knowledge conflicts from three aspects: (i) conflicts encountered in "},"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":"2408.12076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T02:33:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e509486745463d339b262c6564e64229a4b10baea04e51e3d108f7d34f332f57","abstract_canon_sha256":"d5baab89250b75bd950829c5d51eac73335fdfb92534e5a10aa6106cb9f14786"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:03.536957Z","signature_b64":"anQ0N6NnpGNy2CpQ/0aVNI51LRNeHasX3nuhreKXOCYs5/dk6J90pN2uEPxyjHOe1QLPky977OD8FfjnKUQ7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98ceaa179934438a872c08a72bc919d1b2836b884baa054aad4e56f6b09c50e","last_reissued_at":"2026-07-05T08:58:03.536610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:03.536610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiashuo Sun, Juntao Li, Jun Zhang, Min Zhang, Tong Zhu, Xiaoye Qu, Yanshu Li, Yu Cheng, Zhaochen Su","submitted_at":"2024-08-22T02:33:13Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the conflicts between the inherent knowledge of LLMs and the retrieved contextual knowledge. However, a thorough assessment of knowledge conflict in LLMs is still missing. Motivated by this research gap, we present ConflictBank, the first comprehensive benchmark developed to systematically evaluate knowledge conflicts from three aspects: (i) conflicts encountered in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12076","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/2408.12076/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":"2408.12076","created_at":"2026-07-05T08:58:03.536664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12076v1","created_at":"2026-07-05T08:58:03.536664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12076","created_at":"2026-07-05T08:58:03.536664+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGGOVILZSNCD","created_at":"2026-07-05T08:58:03.536664+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGGOVILZSNCDRKDS","created_at":"2026-07-05T08:58:03.536664+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGGOVILZ","created_at":"2026-07-05T08:58:03.536664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01120","citing_title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14368","citing_title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18792","citing_title":"Trust or Abstain? A Self-Aware RAG Approach","ref_index":24,"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":32,"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":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU","json":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU.json","graph_json":"https://pith.science/api/pith-number/ZGGOVILZSNCDRKDSYCFHFPERTU/graph.json","events_json":"https://pith.science/api/pith-number/ZGGOVILZSNCDRKDSYCFHFPERTU/events.json","paper":"https://pith.science/paper/ZGGOVILZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU","download_json":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU.json","view_paper":"https://pith.science/paper/ZGGOVILZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12076&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGGOVILZSNCDRKDSYCFHFPERTU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGGOVILZSNCDRKDSYCFHFPERTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU/action/storage_attestation","attest_author":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU/action/author_attestation","sign_citation":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU/action/citation_signature","submit_replication":"https://pith.science/pith/ZGGOVILZSNCDRKDSYCFHFPERTU/action/replication_record"}},"created_at":"2026-07-05T08:58:03.536664+00:00","updated_at":"2026-07-05T08:58:03.536664+00:00"}