{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WXIZJYRI3AFHM5YVYMZWF5GSJB","short_pith_number":"pith:WXIZJYRI","schema_version":"1.0","canonical_sha256":"b5d194e228d80a767715c33362f4d2487f3ba6edc79d6a29d78a73cf7b01ee59","source":{"kind":"arxiv","id":"2307.13896","version":1},"attestation_state":"computed","paper":{"title":"Low-Parameter Federated Learning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenyou Fan, Jingang Jiang, Xiangyang Liu","submitted_at":"2023-07-26T01:44:02Z","abstract_excerpt":"We study few-shot Natural Language Understanding (NLU) tasks with Large Language Models (LLMs) in federated learning (FL) scenarios. It is a challenging task due to limited labeled data and communication capacities in FL, especially with mobile devices. Recent studies show LLMs can be prompted to perform few-shot NLU tasks like sentiment analysis and arithmetic reasoning. However, the huge sizes of LLMs result in high computation and communication costs, making classical FL schemes impractical. To address these challenges, we propose Low-Parameter Federated Learning (LP-FL). LP-FL combines few"},"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":"2307.13896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-07-26T01:44:02Z","cross_cats_sorted":[],"title_canon_sha256":"8f71be4c4c0c76f7a03a5d25e227f08fac39c69f7cf8ea7931134ad04c314f28","abstract_canon_sha256":"2b5a5cc808f84578a43f0ab627ebc386c79a503e04d5ab985e42857832c05d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:54.715551Z","signature_b64":"bamSbzlrGfefuv0AkZW1x+IhH1ZL+ibJRN4LSR4N1vBqo8g3GwUZFYtPUiFDZCyL+vS7N9zzGKm/sVuVQjsVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d194e228d80a767715c33362f4d2487f3ba6edc79d6a29d78a73cf7b01ee59","last_reissued_at":"2026-07-05T06:34:54.715120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:54.715120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Parameter Federated Learning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenyou Fan, Jingang Jiang, Xiangyang Liu","submitted_at":"2023-07-26T01:44:02Z","abstract_excerpt":"We study few-shot Natural Language Understanding (NLU) tasks with Large Language Models (LLMs) in federated learning (FL) scenarios. It is a challenging task due to limited labeled data and communication capacities in FL, especially with mobile devices. Recent studies show LLMs can be prompted to perform few-shot NLU tasks like sentiment analysis and arithmetic reasoning. However, the huge sizes of LLMs result in high computation and communication costs, making classical FL schemes impractical. To address these challenges, we propose Low-Parameter Federated Learning (LP-FL). LP-FL combines few"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13896","kind":"arxiv","version":1},"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/2307.13896/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":"2307.13896","created_at":"2026-07-05T06:34:54.715185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13896v1","created_at":"2026-07-05T06:34:54.715185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13896","created_at":"2026-07-05T06:34:54.715185+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXIZJYRI3AFH","created_at":"2026-07-05T06:34:54.715185+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXIZJYRI3AFHM5YV","created_at":"2026-07-05T06:34:54.715185+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXIZJYRI","created_at":"2026-07-05T06:34:54.715185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18432","citing_title":"A New Pathway to Integrated Learning and Communication (ILAC): Large AI Model and Hyperdimensional Computing for Communication","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB","json":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB.json","graph_json":"https://pith.science/api/pith-number/WXIZJYRI3AFHM5YVYMZWF5GSJB/graph.json","events_json":"https://pith.science/api/pith-number/WXIZJYRI3AFHM5YVYMZWF5GSJB/events.json","paper":"https://pith.science/paper/WXIZJYRI"},"agent_actions":{"view_html":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB","download_json":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB.json","view_paper":"https://pith.science/paper/WXIZJYRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13896&json=true","fetch_graph":"https://pith.science/api/pith-number/WXIZJYRI3AFHM5YVYMZWF5GSJB/graph.json","fetch_events":"https://pith.science/api/pith-number/WXIZJYRI3AFHM5YVYMZWF5GSJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB/action/storage_attestation","attest_author":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB/action/author_attestation","sign_citation":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB/action/citation_signature","submit_replication":"https://pith.science/pith/WXIZJYRI3AFHM5YVYMZWF5GSJB/action/replication_record"}},"created_at":"2026-07-05T06:34:54.715185+00:00","updated_at":"2026-07-05T06:34:54.715185+00:00"}