{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB","short_pith_number":"pith:EYDHFGU7","schema_version":"1.0","canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","source":{"kind":"arxiv","id":"2510.11194","version":3},"attestation_state":"computed","paper":{"title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peiming Li, Shiyu Li, Xi Chen, Yang Tang, Zhiyuan Hu","submitted_at":"2025-10-13T09:26:47Z","abstract_excerpt":"Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a"},"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":"2510.11194","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","cross_cats_sorted":[],"title_canon_sha256":"42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590","abstract_canon_sha256":"9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:33.600279Z","signature_b64":"wAt90CkGUsAnPGHd/5GZQZnvVkL2mOy/Q8CTPNXPcZtkBIDS3GR0Rc+o5fMUk2U8Zea6iZTzajI6Hbh7mYzvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","last_reissued_at":"2026-06-04T01:08:33.599423Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:33.599423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peiming Li, Shiyu Li, Xi Chen, Yang Tang, Zhiyuan Hu","submitted_at":"2025-10-13T09:26:47Z","abstract_excerpt":"Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e91c24ba52e64970a228d3d5a66e350a0fb76c1094886baa42c91f765cb16aec"},"source":{"id":"2510.11194","kind":"arxiv","version":3},"verdict":{"id":"2a53780c-9319-497a-bcb6-acc29a7cc340","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T08:07:56.171496Z","strongest_claim":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.","one_line_summary":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation.","pith_extraction_headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.11194/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":"2510.11194","created_at":"2026-06-04T01:08:33.599537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.11194v3","created_at":"2026-06-04T01:08:33.599537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11194","created_at":"2026-06-04T01:08:33.599537+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYDHFGU7MCNE","created_at":"2026-06-04T01:08:33.599537+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYDHFGU7MCNEAPBZ","created_at":"2026-06-04T01:08:33.599537+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYDHFGU7","created_at":"2026-06-04T01:08:33.599537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB","json":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB.json","graph_json":"https://pith.science/api/pith-number/EYDHFGU7MCNEAPBZ7OSMLKHOWB/graph.json","events_json":"https://pith.science/api/pith-number/EYDHFGU7MCNEAPBZ7OSMLKHOWB/events.json","paper":"https://pith.science/paper/EYDHFGU7"},"agent_actions":{"view_html":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB","download_json":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB.json","view_paper":"https://pith.science/paper/EYDHFGU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.11194&json=true","fetch_graph":"https://pith.science/api/pith-number/EYDHFGU7MCNEAPBZ7OSMLKHOWB/graph.json","fetch_events":"https://pith.science/api/pith-number/EYDHFGU7MCNEAPBZ7OSMLKHOWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/action/storage_attestation","attest_author":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/action/author_attestation","sign_citation":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/action/citation_signature","submit_replication":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/action/replication_record"}},"created_at":"2026-06-04T01:08:33.599537+00:00","updated_at":"2026-06-04T01:08:33.599537+00:00"}