{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LFLZX2EMQPMC737343IV3WYXLQ","short_pith_number":"pith:LFLZX2EM","schema_version":"1.0","canonical_sha256":"59579be88c83d82feffbe6d15ddb175c0beee403b58dfbbff2fef862c909d76b","source":{"kind":"arxiv","id":"2502.03699","version":3},"attestation_state":"computed","paper":{"title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Jiawei Han, Jinsung Yoon, Sercan O. Arik, Wei Xiong, Yu Meng, Zhen Qin, Ziqi Wang","submitted_at":"2025-02-06T01:22:06Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges like misinformation, hallucinations, bias and misuse. While existing Reinforcement Learning (RL)-based alignment methods are notoriously complex, direct optimization approaches offer a simpler alternative. In this work, we introduce a novel direct optimization approach for LLM alignment by drawing on e"},"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":"2502.03699","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T01:22:06Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"667a37e9f3d5b253d42e33867526a6d4570e54657e8d019dc1bed29a1951ea49","abstract_canon_sha256":"edea45ee799fa2e60ee9ea5e76454bc6fa5b67fefe81e07bcff1b27ffcf376c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:25.518426Z","signature_b64":"K1rRtANUjS0j3v5/7Fk8Y+nEa//cJR2kjdrT12W/3lEqjmq0+UWViqpLMTranqtVHSgwVEeqslsVz5t+IiVWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59579be88c83d82feffbe6d15ddb175c0beee403b58dfbbff2fef862c909d76b","last_reissued_at":"2026-07-05T11:42:25.517816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:25.517816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Jiawei Han, Jinsung Yoon, Sercan O. Arik, Wei Xiong, Yu Meng, Zhen Qin, Ziqi Wang","submitted_at":"2025-02-06T01:22:06Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges like misinformation, hallucinations, bias and misuse. While existing Reinforcement Learning (RL)-based alignment methods are notoriously complex, direct optimization approaches offer a simpler alternative. In this work, we introduce a novel direct optimization approach for LLM alignment by drawing on e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03699","kind":"arxiv","version":3},"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/2502.03699/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":"2502.03699","created_at":"2026-07-05T11:42:25.517886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03699v3","created_at":"2026-07-05T11:42:25.517886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03699","created_at":"2026-07-05T11:42:25.517886+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFLZX2EMQPMC","created_at":"2026-07-05T11:42:25.517886+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFLZX2EMQPMC7373","created_at":"2026-07-05T11:42:25.517886+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFLZX2EM","created_at":"2026-07-05T11:42:25.517886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15117","citing_title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ","json":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ.json","graph_json":"https://pith.science/api/pith-number/LFLZX2EMQPMC737343IV3WYXLQ/graph.json","events_json":"https://pith.science/api/pith-number/LFLZX2EMQPMC737343IV3WYXLQ/events.json","paper":"https://pith.science/paper/LFLZX2EM"},"agent_actions":{"view_html":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ","download_json":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ.json","view_paper":"https://pith.science/paper/LFLZX2EM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03699&json=true","fetch_graph":"https://pith.science/api/pith-number/LFLZX2EMQPMC737343IV3WYXLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LFLZX2EMQPMC737343IV3WYXLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ/action/storage_attestation","attest_author":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ/action/author_attestation","sign_citation":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ/action/citation_signature","submit_replication":"https://pith.science/pith/LFLZX2EMQPMC737343IV3WYXLQ/action/replication_record"}},"created_at":"2026-07-05T11:42:25.517886+00:00","updated_at":"2026-07-05T11:42:25.517886+00:00"}