{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E2CEIY3NNWVQDOORIHO44KWOQF","short_pith_number":"pith:E2CEIY3N","schema_version":"1.0","canonical_sha256":"268444636d6dab01b9d141ddce2ace81791808032b88cb8bc083a29f79931534","source":{"kind":"arxiv","id":"2406.02224","version":4},"attestation_state":"computed","paper":{"title":"FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guoqiang Ma, Hanlin Gu, Kai Chen, Lixin Fan, Qiang Yang, Tao Fan, Yan Kang, Yuanfeng Song","submitted_at":"2024-06-04T11:36:09Z","abstract_excerpt":"Recent research in federated large language models (LLMs) has primarily focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLMs to small language models (SLMs) at downstream clients. However, a significant gap remains in the simultaneous mutual enhancement of both the server's LLM and clients' SLMs. To bridge this gap, we propose FedMKT, a parameter-efficient federated mutual knowledge transfer framework for large and small language models. This framework is designed to adaptively transfer knowledge fr"},"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":"2406.02224","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T11:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea8bd948f824464b4641afa0e13fa3f41cd64554b0e1cf28550c54f6d9c5894c","abstract_canon_sha256":"9c05de69d7648e855cc3124f46933be050a31830d1e1ba4ef557ba30b1abe2c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:43.075325Z","signature_b64":"xPVbDTIZHDCJJABIS0sKaFXgNe16nBHNvsUNq2RVYTv45xptd8BAylDNednfPA3eZYjV/pKRdaE8O8z8OnM8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"268444636d6dab01b9d141ddce2ace81791808032b88cb8bc083a29f79931534","last_reissued_at":"2026-07-05T09:49:43.074823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:43.074823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guoqiang Ma, Hanlin Gu, Kai Chen, Lixin Fan, Qiang Yang, Tao Fan, Yan Kang, Yuanfeng Song","submitted_at":"2024-06-04T11:36:09Z","abstract_excerpt":"Recent research in federated large language models (LLMs) has primarily focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLMs to small language models (SLMs) at downstream clients. However, a significant gap remains in the simultaneous mutual enhancement of both the server's LLM and clients' SLMs. To bridge this gap, we propose FedMKT, a parameter-efficient federated mutual knowledge transfer framework for large and small language models. This framework is designed to adaptively transfer knowledge fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02224","kind":"arxiv","version":4},"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/2406.02224/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":"2406.02224","created_at":"2026-07-05T09:49:43.074880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02224v4","created_at":"2026-07-05T09:49:43.074880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02224","created_at":"2026-07-05T09:49:43.074880+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2CEIY3NNWVQ","created_at":"2026-07-05T09:49:43.074880+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2CEIY3NNWVQDOOR","created_at":"2026-07-05T09:49:43.074880+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2CEIY3N","created_at":"2026-07-05T09:49:43.074880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF","json":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF.json","graph_json":"https://pith.science/api/pith-number/E2CEIY3NNWVQDOORIHO44KWOQF/graph.json","events_json":"https://pith.science/api/pith-number/E2CEIY3NNWVQDOORIHO44KWOQF/events.json","paper":"https://pith.science/paper/E2CEIY3N"},"agent_actions":{"view_html":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF","download_json":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF.json","view_paper":"https://pith.science/paper/E2CEIY3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02224&json=true","fetch_graph":"https://pith.science/api/pith-number/E2CEIY3NNWVQDOORIHO44KWOQF/graph.json","fetch_events":"https://pith.science/api/pith-number/E2CEIY3NNWVQDOORIHO44KWOQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF/action/storage_attestation","attest_author":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF/action/author_attestation","sign_citation":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF/action/citation_signature","submit_replication":"https://pith.science/pith/E2CEIY3NNWVQDOORIHO44KWOQF/action/replication_record"}},"created_at":"2026-07-05T09:49:43.074880+00:00","updated_at":"2026-07-05T09:49:43.074880+00:00"}