{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OPCVJNQ3JDPIMOQMAGZBTFYCZX","short_pith_number":"pith:OPCVJNQ3","schema_version":"1.0","canonical_sha256":"73c554b61b48de863a0c01b2199702cdd72a8b18875c7f47a42bcf67281bf720","source":{"kind":"arxiv","id":"2403.16649","version":2},"attestation_state":"computed","paper":{"title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengming Li, Feiteng Fang, Jinchang Hou, Liang Zhu, Min Yang, Qixuan Zhao, Ruifeng Xu, Xi Feng, Xiping Hu","submitted_at":"2024-03-25T11:37:15Z","abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding challenge in human alignment techniques based on reinforcement learning lies in their inherent complexity and difficulty in training. To address this challenge, we present a simple yet effective Contrastive Learning Framework for Human Alignment (CLHA) to align LLMs with human preferences directly. CLHA employs a novel rescoring strategy to evaluate the noise w"},"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":"2403.16649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-25T11:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"6441c32c1f832d3008c2061b391039d7e5c96e30666c29e507aa64d7f94a689a","abstract_canon_sha256":"d037f95ad8c4991a1b7d0af6299da3467b4273e1c182a524b1ac013ac98e8463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:43.671891Z","signature_b64":"GrHZjHiqR9t80JYM5JJ16LEJyqQpUzV3Elya1FdbXsu0ImSvILYWhWtkaPO14KltRQW3mYx4WqtjbY5UdD4WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73c554b61b48de863a0c01b2199702cdd72a8b18875c7f47a42bcf67281bf720","last_reissued_at":"2026-07-05T08:00:43.671418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:43.671418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengming Li, Feiteng Fang, Jinchang Hou, Liang Zhu, Min Yang, Qixuan Zhao, Ruifeng Xu, Xi Feng, Xiping Hu","submitted_at":"2024-03-25T11:37:15Z","abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding challenge in human alignment techniques based on reinforcement learning lies in their inherent complexity and difficulty in training. To address this challenge, we present a simple yet effective Contrastive Learning Framework for Human Alignment (CLHA) to align LLMs with human preferences directly. CLHA employs a novel rescoring strategy to evaluate the noise w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16649","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/2403.16649/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":"2403.16649","created_at":"2026-07-05T08:00:43.671482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16649v2","created_at":"2026-07-05T08:00:43.671482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16649","created_at":"2026-07-05T08:00:43.671482+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPCVJNQ3JDPI","created_at":"2026-07-05T08:00:43.671482+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPCVJNQ3JDPIMOQM","created_at":"2026-07-05T08:00:43.671482+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPCVJNQ3","created_at":"2026-07-05T08:00:43.671482+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/OPCVJNQ3JDPIMOQMAGZBTFYCZX","json":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX.json","graph_json":"https://pith.science/api/pith-number/OPCVJNQ3JDPIMOQMAGZBTFYCZX/graph.json","events_json":"https://pith.science/api/pith-number/OPCVJNQ3JDPIMOQMAGZBTFYCZX/events.json","paper":"https://pith.science/paper/OPCVJNQ3"},"agent_actions":{"view_html":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX","download_json":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX.json","view_paper":"https://pith.science/paper/OPCVJNQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16649&json=true","fetch_graph":"https://pith.science/api/pith-number/OPCVJNQ3JDPIMOQMAGZBTFYCZX/graph.json","fetch_events":"https://pith.science/api/pith-number/OPCVJNQ3JDPIMOQMAGZBTFYCZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX/action/storage_attestation","attest_author":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX/action/author_attestation","sign_citation":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX/action/citation_signature","submit_replication":"https://pith.science/pith/OPCVJNQ3JDPIMOQMAGZBTFYCZX/action/replication_record"}},"created_at":"2026-07-05T08:00:43.671482+00:00","updated_at":"2026-07-05T08:00:43.671482+00:00"}