{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5V4IJFRK5QCAKRNHZDUCQOOHIG","short_pith_number":"pith:5V4IJFRK","schema_version":"1.0","canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","source":{"kind":"arxiv","id":"2410.14745","version":2},"attestation_state":"computed","paper":{"title":"Semi-supervised Fine-tuning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junyu Luo, Ming Zhang, Wei Ju, Xiao Luo, Xiusi Chen, Zhiping Xiao","submitted_at":"2024-10-17T16:59:46Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial in adapting large language model (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in yielding satisfactory results. Therefore, a data-efficient framework that can fully exploit labeled and unlabeled data for LLM fine-tuning is highly anticipated.Towards this end, we introduce a semi-supervised fine-tuning(SemiFT) task and a framework named SemiEvol for LLM alignment from a propagate-and-select manner. For knowledge propagation, SemiEvol adopt"},"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":"2410.14745","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"284cef47ec7bb1793f2fec8619c0276abac649662915da5d115cd2bd9e0d3b3b","abstract_canon_sha256":"dd53ebbd0f6d5d0b46bc441610126042e643cf465dc831101b4768533dafeac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:59.164021Z","signature_b64":"bpYPCDFqMPjcQ08xDMRYCGIfj79c2x4aT/YUoFAoei9YjUtRSOAVOyze2CIzUdFzgIHvZ1y1MEXD/3FBJKmSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","last_reissued_at":"2026-07-05T10:16:59.163602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:59.163602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Fine-tuning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junyu Luo, Ming Zhang, Wei Ju, Xiao Luo, Xiusi Chen, Zhiping Xiao","submitted_at":"2024-10-17T16:59:46Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial in adapting large language model (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in yielding satisfactory results. Therefore, a data-efficient framework that can fully exploit labeled and unlabeled data for LLM fine-tuning is highly anticipated.Towards this end, we introduce a semi-supervised fine-tuning(SemiFT) task and a framework named SemiEvol for LLM alignment from a propagate-and-select manner. For knowledge propagation, SemiEvol adopt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14745","kind":"arxiv","version":2},"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/2410.14745/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":"2410.14745","created_at":"2026-07-05T10:16:59.163660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14745v2","created_at":"2026-07-05T10:16:59.163660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14745","created_at":"2026-07-05T10:16:59.163660+00:00"},{"alias_kind":"pith_short_12","alias_value":"5V4IJFRK5QCA","created_at":"2026-07-05T10:16:59.163660+00:00"},{"alias_kind":"pith_short_16","alias_value":"5V4IJFRK5QCAKRNH","created_at":"2026-07-05T10:16:59.163660+00:00"},{"alias_kind":"pith_short_8","alias_value":"5V4IJFRK","created_at":"2026-07-05T10:16:59.163660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.08444","citing_title":"Learned iterative networks: An operator learning perspective","ref_index":107,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG","json":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG.json","graph_json":"https://pith.science/api/pith-number/5V4IJFRK5QCAKRNHZDUCQOOHIG/graph.json","events_json":"https://pith.science/api/pith-number/5V4IJFRK5QCAKRNHZDUCQOOHIG/events.json","paper":"https://pith.science/paper/5V4IJFRK"},"agent_actions":{"view_html":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG","download_json":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG.json","view_paper":"https://pith.science/paper/5V4IJFRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14745&json=true","fetch_graph":"https://pith.science/api/pith-number/5V4IJFRK5QCAKRNHZDUCQOOHIG/graph.json","fetch_events":"https://pith.science/api/pith-number/5V4IJFRK5QCAKRNHZDUCQOOHIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/action/storage_attestation","attest_author":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/action/author_attestation","sign_citation":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/action/citation_signature","submit_replication":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/action/replication_record"}},"created_at":"2026-07-05T10:16:59.163660+00:00","updated_at":"2026-07-05T10:16:59.163660+00:00"}