{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6FLPXZIH27I6YH7YQEOX4LIOB","short_pith_number":"pith:M6FLPXZI","schema_version":"1.0","canonical_sha256":"678ab7df283ebe8f60ffc408ebf16870706d54f34d0e04da81911d0c9fc1afc2","source":{"kind":"arxiv","id":"2402.11782","version":2},"attestation_state":"computed","paper":{"title":"What Evidence Do Language Models Find Convincing?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Wan, Dan Klein, Eric Wallace","submitted_at":"2024-02-19T02:15:34Z","abstract_excerpt":"Retrieval-augmented language models are being increasingly tasked with subjective, contentious, and conflicting queries such as \"is aspartame linked to cancer\". To resolve these ambiguous queries, one must search through a large range of websites and consider \"which, if any, of this evidence do I find convincing?\". In this work, we study how LLMs answer this question. In particular, we construct ConflictingQA, a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts (e.g., quantitative results), argument styles (e.g., appeals to aut"},"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":"2402.11782","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T02:15:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"07be849376de61c6ff51f60163ba457724124d622cb3c69f40a8463cd526ac38","abstract_canon_sha256":"366b8901f8da364648ac59e5865d3f1cfde3230d328b529df31877d61df6a43d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:39.155134Z","signature_b64":"I6PeRnhBnj1iq/xgxcQYDHwstjFq7FzNKRCrec/E4V3pkMlt8alNZmKSJcwNRCE6DYmXtvMRQkZejAKrvpR5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"678ab7df283ebe8f60ffc408ebf16870706d54f34d0e04da81911d0c9fc1afc2","last_reissued_at":"2026-07-05T08:53:39.154647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:39.154647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Evidence Do Language Models Find Convincing?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Wan, Dan Klein, Eric Wallace","submitted_at":"2024-02-19T02:15:34Z","abstract_excerpt":"Retrieval-augmented language models are being increasingly tasked with subjective, contentious, and conflicting queries such as \"is aspartame linked to cancer\". To resolve these ambiguous queries, one must search through a large range of websites and consider \"which, if any, of this evidence do I find convincing?\". In this work, we study how LLMs answer this question. In particular, we construct ConflictingQA, a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts (e.g., quantitative results), argument styles (e.g., appeals to aut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11782","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/2402.11782/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":"2402.11782","created_at":"2026-07-05T08:53:39.154709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11782v2","created_at":"2026-07-05T08:53:39.154709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11782","created_at":"2026-07-05T08:53:39.154709+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6FLPXZIH27I","created_at":"2026-07-05T08:53:39.154709+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6FLPXZIH27I6YH7","created_at":"2026-07-05T08:53:39.154709+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6FLPXZI","created_at":"2026-07-05T08:53:39.154709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22266","citing_title":"Large Language Models Decide Early and Explain Later","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB","json":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB.json","graph_json":"https://pith.science/api/pith-number/M6FLPXZIH27I6YH7YQEOX4LIOB/graph.json","events_json":"https://pith.science/api/pith-number/M6FLPXZIH27I6YH7YQEOX4LIOB/events.json","paper":"https://pith.science/paper/M6FLPXZI"},"agent_actions":{"view_html":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB","download_json":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB.json","view_paper":"https://pith.science/paper/M6FLPXZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11782&json=true","fetch_graph":"https://pith.science/api/pith-number/M6FLPXZIH27I6YH7YQEOX4LIOB/graph.json","fetch_events":"https://pith.science/api/pith-number/M6FLPXZIH27I6YH7YQEOX4LIOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB/action/storage_attestation","attest_author":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB/action/author_attestation","sign_citation":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB/action/citation_signature","submit_replication":"https://pith.science/pith/M6FLPXZIH27I6YH7YQEOX4LIOB/action/replication_record"}},"created_at":"2026-07-05T08:53:39.154709+00:00","updated_at":"2026-07-05T08:53:39.154709+00:00"}