{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UVXB45G5NWMUO23SD2UMHWEHTB","short_pith_number":"pith:UVXB45G5","schema_version":"1.0","canonical_sha256":"a56e1e74dd6d99476b721ea8c3d887984342ca1ae8cc41ad3a87d9783a31ea6d","source":{"kind":"arxiv","id":"2501.01336","version":1},"attestation_state":"computed","paper":{"title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"See-kiong Ng, Tat-Seng Chua, Yang Deng, Yong Zhao","submitted_at":"2025-01-02T16:38:21Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confid"},"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":"2501.01336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T16:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"e2c78311ca2a39326fc9dbed736f18236997546a7ec349cb401882f8f4f98bcc","abstract_canon_sha256":"5575a526f3ffc19897ff21b6a34f635e30959cf3cd14e9e37950dfd1dc0d4b47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:18.397895Z","signature_b64":"CZ1Hr9QBOXJsu/3TjUFe9Jr89Ei6vVPc3auYD+qXso5hcvta2DdQN9TNUo2fs4sB5XhGYDEb4QxjvS5iHBb4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56e1e74dd6d99476b721ea8c3d887984342ca1ae8cc41ad3a87d9783a31ea6d","last_reissued_at":"2026-07-05T09:56:18.397422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:18.397422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"See-kiong Ng, Tat-Seng Chua, Yang Deng, Yong Zhao","submitted_at":"2025-01-02T16:38:21Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01336","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/2501.01336/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":"2501.01336","created_at":"2026-07-05T09:56:18.397480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01336v1","created_at":"2026-07-05T09:56:18.397480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01336","created_at":"2026-07-05T09:56:18.397480+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVXB45G5NWMU","created_at":"2026-07-05T09:56:18.397480+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVXB45G5NWMUO23S","created_at":"2026-07-05T09:56:18.397480+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVXB45G5","created_at":"2026-07-05T09:56:18.397480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17873","citing_title":"Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB","json":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB.json","graph_json":"https://pith.science/api/pith-number/UVXB45G5NWMUO23SD2UMHWEHTB/graph.json","events_json":"https://pith.science/api/pith-number/UVXB45G5NWMUO23SD2UMHWEHTB/events.json","paper":"https://pith.science/paper/UVXB45G5"},"agent_actions":{"view_html":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB","download_json":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB.json","view_paper":"https://pith.science/paper/UVXB45G5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01336&json=true","fetch_graph":"https://pith.science/api/pith-number/UVXB45G5NWMUO23SD2UMHWEHTB/graph.json","fetch_events":"https://pith.science/api/pith-number/UVXB45G5NWMUO23SD2UMHWEHTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB/action/storage_attestation","attest_author":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB/action/author_attestation","sign_citation":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB/action/citation_signature","submit_replication":"https://pith.science/pith/UVXB45G5NWMUO23SD2UMHWEHTB/action/replication_record"}},"created_at":"2026-07-05T09:56:18.397480+00:00","updated_at":"2026-07-05T09:56:18.397480+00:00"}