{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7PG2TQVHYVXNARPW6CZSFBRGA","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":"da2c792b1a4f6433da75ee56efa093c7a4ed4440b6ea01fd43c4fe94a5450f8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T14:23:57Z","title_canon_sha256":"d506afd100340f3ba131e5a4b935bcb7b62e76c4c57c5ce46f6f35c9e42c629c"},"schema_version":"1.0","source":{"id":"2406.15178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15178","created_at":"2026-07-05T08:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15178v1","created_at":"2026-07-05T08:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15178","created_at":"2026-07-05T08:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"M7PG2TQVHYVX","created_at":"2026-07-05T08:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"M7PG2TQVHYVXNARP","created_at":"2026-07-05T08:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"M7PG2TQV","created_at":"2026-07-05T08:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:78852b001a17b5551b5e1d1d78c450afe9198f69f1964ceb8b12e0f5ca3f0076","target":"graph","created_at":"2026-07-05T08:35:15Z","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/2406.15178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and human-preference alignment. However, aligning LLMs with these objectives in sequence suffers from an inherent problem: the objectives may conflict, and the LLMs cannot guarantee to simultaneously align with the instructions and human preferences well. To response to these, in this work, we propose a Hybrid Alignment Training (Hbat) approach, based on alternating alignmen","authors_text":"Bei Li, Chenglong Wang, Hang Zhou, Jingbo Zhu, Kaiyan Chang, Tongran Liu, Tong Xiao, Yongyu Mu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T14:23:57Z","title":"Hybrid Alignment Training for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15178","kind":"arxiv","version":1},"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:f28cd0b82f8f89dbbe5301477f15dedad123d58def66ae04ba0ee72b59132e15","target":"record","created_at":"2026-07-05T08:35:15Z","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":"da2c792b1a4f6433da75ee56efa093c7a4ed4440b6ea01fd43c4fe94a5450f8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T14:23:57Z","title_canon_sha256":"d506afd100340f3ba131e5a4b935bcb7b62e76c4c57c5ce46f6f35c9e42c629c"},"schema_version":"1.0","source":{"id":"2406.15178","kind":"arxiv","version":1}},"canonical_sha256":"67de6d4e153e2b76822fb78599143130388051703433f62200e51ddadb2dd7f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67de6d4e153e2b76822fb78599143130388051703433f62200e51ddadb2dd7f6","first_computed_at":"2026-07-05T08:35:15.046184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:15.046184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xeLvSLQZxb2GWmogpPBrqJO46oD2WU74OAdVpyuZ4G4D078nPalqZq6enzhCcxNR0vynC+kdvYRJs1YxunbADg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:15.046644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f28cd0b82f8f89dbbe5301477f15dedad123d58def66ae04ba0ee72b59132e15","sha256:78852b001a17b5551b5e1d1d78c450afe9198f69f1964ceb8b12e0f5ca3f0076"],"state_sha256":"fb10641d6cbe28fa3e3a7689adf13e9de0c5a06ac8ecf2deab03e996c4c42b2e"}