{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z4CLG6CLMTBQEKJMILM4FFNO4Y","short_pith_number":"pith:Z4CLG6CL","schema_version":"1.0","canonical_sha256":"cf04b3784b64c302292c42d9c295aee631b612182be5f851d69a5b7e8fe006c9","source":{"kind":"arxiv","id":"2310.15080","version":3},"attestation_state":"computed","paper":{"title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dejing Dou, Huaiyu Dai, Jiaxiang Ren, Ji Liu, Jiwen Zhou, Tianshi Che, Victor S. Sheng, Yang Zhou","submitted_at":"2023-10-23T16:37:59Z","abstract_excerpt":"Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which limits the applicability of FL techniques to tackle the LLMs in real scenarios. Prompt tuning can significantly reduce the number of parameters to update, but it either incurs performance degradation or low training efficiency. The straightforward utilization of prompt tuning in the FL often raises non-trivial communication costs and dramatically degrades perform"},"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":"2310.15080","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T16:37:59Z","cross_cats_sorted":["cs.CL","cs.DC"],"title_canon_sha256":"e6207c0c16c0d7c7219e92c7245f7c5c4eed27cb4a4d455568ad7a53c7bdff59","abstract_canon_sha256":"95420c70d83588679f92a0e3160d03076051bbe7ef5562d601425d7edf809e6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:56.830047Z","signature_b64":"wm6KCCO8jbYdVuf+UQWu/N2gzoqo6DnULOtoZ6x/kL2GJtrIzZPpEvvnrqp7K5PF+zhZsj0qaWC9fDVbztT5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf04b3784b64c302292c42d9c295aee631b612182be5f851d69a5b7e8fe006c9","last_reissued_at":"2026-07-05T07:43:56.829546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:56.829546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dejing Dou, Huaiyu Dai, Jiaxiang Ren, Ji Liu, Jiwen Zhou, Tianshi Che, Victor S. Sheng, Yang Zhou","submitted_at":"2023-10-23T16:37:59Z","abstract_excerpt":"Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which limits the applicability of FL techniques to tackle the LLMs in real scenarios. Prompt tuning can significantly reduce the number of parameters to update, but it either incurs performance degradation or low training efficiency. The straightforward utilization of prompt tuning in the FL often raises non-trivial communication costs and dramatically degrades perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15080","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/2310.15080/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":"2310.15080","created_at":"2026-07-05T07:43:56.829603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15080v3","created_at":"2026-07-05T07:43:56.829603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15080","created_at":"2026-07-05T07:43:56.829603+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4CLG6CLMTBQ","created_at":"2026-07-05T07:43:56.829603+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4CLG6CLMTBQEKJM","created_at":"2026-07-05T07:43:56.829603+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4CLG6CL","created_at":"2026-07-05T07:43:56.829603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":150,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y","json":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y.json","graph_json":"https://pith.science/api/pith-number/Z4CLG6CLMTBQEKJMILM4FFNO4Y/graph.json","events_json":"https://pith.science/api/pith-number/Z4CLG6CLMTBQEKJMILM4FFNO4Y/events.json","paper":"https://pith.science/paper/Z4CLG6CL"},"agent_actions":{"view_html":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y","download_json":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y.json","view_paper":"https://pith.science/paper/Z4CLG6CL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15080&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4CLG6CLMTBQEKJMILM4FFNO4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4CLG6CLMTBQEKJMILM4FFNO4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y/action/storage_attestation","attest_author":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y/action/author_attestation","sign_citation":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y/action/citation_signature","submit_replication":"https://pith.science/pith/Z4CLG6CLMTBQEKJMILM4FFNO4Y/action/replication_record"}},"created_at":"2026-07-05T07:43:56.829603+00:00","updated_at":"2026-07-05T07:43:56.829603+00:00"}