{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QVWQLNQNISJAIWNQMRZNPJXGJ5","short_pith_number":"pith:QVWQLNQN","schema_version":"1.0","canonical_sha256":"856d05b60d44920459b06472d7a6e64f4c28104f76be81b91014f0c27e7eb6e0","source":{"kind":"arxiv","id":"2506.08500","version":2},"attestation_state":"computed","paper":{"title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Arie Cattan, Avi Caciularu, Eran Ofek, Idan Szpektor, Jonathan Herzig, Ori Ram, Roee Aharoni, Sasha Goldshtein","submitted_at":"2025-06-10T06:52:57Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is a commonly used approach for enhancing large language models (LLMs) with relevant and up-to-date information. However, the retrieved sources can often contain conflicting information and it remains unclear how models should address such discrepancies. In this work, we first propose a novel taxonomy of knowledge conflict types in RAG, along with the desired model behavior for each type. We then introduce CONFLICTS, a high-quality benchmark with expert annotations of conflict types in a realistic RAG setting. CONFLICTS is the first benchmark that enables t"},"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":"2506.08500","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T06:52:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1bc099398e08a8ccddf22d1916f6e71d80f8cca47196bdcf6671b478a2c3e63d","abstract_canon_sha256":"b94ecbd133be9273050bd6aa042e58162423de7c58f38ffa184a9e8260beb8d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:48.975026Z","signature_b64":"7MzDry/dDTMxZrBpZOcZw/X0fRuhGka79v5OgYdFYI6kThMrtoPXQ1zPyh3KJSr9M2C89Ms/mmRxYKuNASwcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"856d05b60d44920459b06472d7a6e64f4c28104f76be81b91014f0c27e7eb6e0","last_reissued_at":"2026-07-05T11:21:48.974547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:48.974547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Arie Cattan, Avi Caciularu, Eran Ofek, Idan Szpektor, Jonathan Herzig, Ori Ram, Roee Aharoni, Sasha Goldshtein","submitted_at":"2025-06-10T06:52:57Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is a commonly used approach for enhancing large language models (LLMs) with relevant and up-to-date information. However, the retrieved sources can often contain conflicting information and it remains unclear how models should address such discrepancies. In this work, we first propose a novel taxonomy of knowledge conflict types in RAG, along with the desired model behavior for each type. We then introduce CONFLICTS, a high-quality benchmark with expert annotations of conflict types in a realistic RAG setting. CONFLICTS is the first benchmark that enables t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08500","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/2506.08500/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":"2506.08500","created_at":"2026-07-05T11:21:48.974610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08500v2","created_at":"2026-07-05T11:21:48.974610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08500","created_at":"2026-07-05T11:21:48.974610+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVWQLNQNISJA","created_at":"2026-07-05T11:21:48.974610+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVWQLNQNISJAIWNQ","created_at":"2026-07-05T11:21:48.974610+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVWQLNQN","created_at":"2026-07-05T11:21:48.974610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25191","citing_title":"To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00869","citing_title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12138","citing_title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5","json":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5.json","graph_json":"https://pith.science/api/pith-number/QVWQLNQNISJAIWNQMRZNPJXGJ5/graph.json","events_json":"https://pith.science/api/pith-number/QVWQLNQNISJAIWNQMRZNPJXGJ5/events.json","paper":"https://pith.science/paper/QVWQLNQN"},"agent_actions":{"view_html":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5","download_json":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5.json","view_paper":"https://pith.science/paper/QVWQLNQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08500&json=true","fetch_graph":"https://pith.science/api/pith-number/QVWQLNQNISJAIWNQMRZNPJXGJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/QVWQLNQNISJAIWNQMRZNPJXGJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5/action/storage_attestation","attest_author":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5/action/author_attestation","sign_citation":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5/action/citation_signature","submit_replication":"https://pith.science/pith/QVWQLNQNISJAIWNQMRZNPJXGJ5/action/replication_record"}},"created_at":"2026-07-05T11:21:48.974610+00:00","updated_at":"2026-07-05T11:21:48.974610+00:00"}