{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ECHN6S6W4QRWHB6TNXMGMXPG7I","short_pith_number":"pith:ECHN6S6W","schema_version":"1.0","canonical_sha256":"208edf4bd6e4236387d36dd8665de6fa0a24da5a180433cd9feeb824ce795bd0","source":{"kind":"arxiv","id":"2412.14922","version":1},"attestation_state":"computed","paper":{"title":"RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jingyang Yuan, Junyu Luo, Kaize Ding, Ming Zhang, Xiao Luo, Zhiping Xiao","submitted_at":"2024-12-19T15:00:18Z","abstract_excerpt":"Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical applications, which poses significant challenges to model performance on downstream tasks. Therefore, there is an urgent need for a noise-robust SFT framework to enhance model capabilities in downstream tasks. To address this challenge, we introduce a robust SFT framework (RobustFT) that performs noise detection and relabeling on downstream task data. For noise identi"},"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":"2412.14922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T15:00:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87eb0167d3b65d6fc8ab9bb27b8974d4ad09ae15f87b0ea53a47fa69a35bd355","abstract_canon_sha256":"f25788189f1a9403e8e0ab555fd9964c7ae4009e0e167bcc269a51357a751e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:54.334804Z","signature_b64":"SNj/FvZv3I+79jiNKmpdFdkF1yvQBs9cXg9tqG/QToEd+MMDcwAjqJVJ2xStM++zKWYwn3l98E3Dw+84JGCbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208edf4bd6e4236387d36dd8665de6fa0a24da5a180433cd9feeb824ce795bd0","last_reissued_at":"2026-07-05T09:51:54.334254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:54.334254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jingyang Yuan, Junyu Luo, Kaize Ding, Ming Zhang, Xiao Luo, Zhiping Xiao","submitted_at":"2024-12-19T15:00:18Z","abstract_excerpt":"Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical applications, which poses significant challenges to model performance on downstream tasks. Therefore, there is an urgent need for a noise-robust SFT framework to enhance model capabilities in downstream tasks. To address this challenge, we introduce a robust SFT framework (RobustFT) that performs noise detection and relabeling on downstream task data. For noise identi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14922","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/2412.14922/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":"2412.14922","created_at":"2026-07-05T09:51:54.334312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14922v1","created_at":"2026-07-05T09:51:54.334312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14922","created_at":"2026-07-05T09:51:54.334312+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECHN6S6W4QRW","created_at":"2026-07-05T09:51:54.334312+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECHN6S6W4QRWHB6T","created_at":"2026-07-05T09:51:54.334312+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECHN6S6W","created_at":"2026-07-05T09:51:54.334312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11583","citing_title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13875","citing_title":"Common-agency Games for Multi-Objective Test-Time Alignment","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12469","citing_title":"Analyzing the Effect of Noise in LLM Fine-tuning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17289","citing_title":"REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I","json":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I.json","graph_json":"https://pith.science/api/pith-number/ECHN6S6W4QRWHB6TNXMGMXPG7I/graph.json","events_json":"https://pith.science/api/pith-number/ECHN6S6W4QRWHB6TNXMGMXPG7I/events.json","paper":"https://pith.science/paper/ECHN6S6W"},"agent_actions":{"view_html":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I","download_json":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I.json","view_paper":"https://pith.science/paper/ECHN6S6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14922&json=true","fetch_graph":"https://pith.science/api/pith-number/ECHN6S6W4QRWHB6TNXMGMXPG7I/graph.json","fetch_events":"https://pith.science/api/pith-number/ECHN6S6W4QRWHB6TNXMGMXPG7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I/action/storage_attestation","attest_author":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I/action/author_attestation","sign_citation":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I/action/citation_signature","submit_replication":"https://pith.science/pith/ECHN6S6W4QRWHB6TNXMGMXPG7I/action/replication_record"}},"created_at":"2026-07-05T09:51:54.334312+00:00","updated_at":"2026-07-05T09:51:54.334312+00:00"}