{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BRHDIKEQFYVUEYNYHJOFDMYEPQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dd976dfb6b2c6d8b2bbfe68ea9055987125151c152a7642ca04efae43c0996e9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T08:49:38Z","title_canon_sha256":"c8c0399dac725367951e6eb9468b1dd4d912ba6f1d04e21f3e0447c3010abaf4"},"schema_version":"1.0","source":{"id":"2404.11999","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11999","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11999v5","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11999","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"BRHDIKEQFYVU","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"BRHDIKEQFYVUEYNY","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"BRHDIKEQ","created_at":"2026-07-05T09:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:0bba5faa53ee4d82b8ec51d232b2c1d0f3c665ca765a9837819c31b014bdf7df","target":"graph","created_at":"2026-07-05T09:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.11999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the evaluation of full answers generated by the models. However, the generation of these responses occurs in a token level, following a sequential, auto-regressive fashion. In this paper, we introduce Token-level Direct Preference Optimization (TDPO), a novel approach to align LLMs with human preferences by optimizing policy at the token level. Unlike previous method","authors_text":"Guoqing Liu, Haifeng Zhang, Jun Wang, Ning Yang, Weiyu Ma, Yongcheng Zeng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T08:49:38Z","title":"Token-level Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11999","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4d57b172fe77ef48432605250e529d5957cf6dc10c141d15cb2e7d428e804904","target":"record","created_at":"2026-07-05T09:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dd976dfb6b2c6d8b2bbfe68ea9055987125151c152a7642ca04efae43c0996e9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T08:49:38Z","title_canon_sha256":"c8c0399dac725367951e6eb9468b1dd4d912ba6f1d04e21f3e0447c3010abaf4"},"schema_version":"1.0","source":{"id":"2404.11999","kind":"arxiv","version":5}},"canonical_sha256":"0c4e3428902e2b4261b83a5c51b3047c0a94302027400a610ede05b88bd8065f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c4e3428902e2b4261b83a5c51b3047c0a94302027400a610ede05b88bd8065f","first_computed_at":"2026-07-05T09:00:59.504850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:59.504850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RcpSo7bSt9r0QXCsT/tnaYBJ55hbnfB/wmhQ+YxgHv3LsWtyY2S0bZxTIrM2a/CLt0MtO395u51y7Xn7Q1QiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:59.505339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11999","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d57b172fe77ef48432605250e529d5957cf6dc10c141d15cb2e7d428e804904","sha256:0bba5faa53ee4d82b8ec51d232b2c1d0f3c665ca765a9837819c31b014bdf7df"],"state_sha256":"c0b8a49a3ebc7f5aa6a7057febf81887cdff7fc584b9fd870e801e1126e2c237"}