{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NTYE7PRHYFMDMDUBSF4LQJDH5","short_pith_number":"pith:6NTYE7PR","schema_version":"1.0","canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","source":{"kind":"arxiv","id":"2403.15042","version":2},"attestation_state":"computed","paper":{"title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Gholami, Gopala Anumanchipalli, Karttikeya Mangalam, Kurt Keutzer, Michael W. Mahoney, Nicholas Lee, Sehoon Kim, Sheng Shen, Thanakul Wattanawong","submitted_at":"2024-03-22T08:57:07Z","abstract_excerpt":"Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many of them are in the low-data regime, making fine-tuning challenging. To address this, we propose LLM2LLM, a targeted and iterative data augmentation strategy that uses a teacher LLM to enhance a small seed dataset by augmenting additional data that can be used for fine-tuning on a specific task. LLM2LLM (1) fine-tunes a baseline student LLM on the i"},"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":"2403.15042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-22T08:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"da02c7f73fa5ab1a5172a70d4504b927c9dfd47a08a234be2f09904b481af9ba","abstract_canon_sha256":"5b8d7e28e9fb18f3fe717987fa7be8f9372d371bd5f66d0ab60a804cf7ab47dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:27.334978Z","signature_b64":"jCo0r0FyJR2YHiPADPZO6SKBIBC1MzOyAdGklKvDQSEXGx+eSWrTfGD/7e5GGfEkflP8GuhIK/yW8gyHgIFdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f367827df13e0ac1b0740c8bc5c1233f785fee6913f9a11464b947e4c850cac6","last_reissued_at":"2026-07-05T08:43:27.334512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:27.334512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Gholami, Gopala Anumanchipalli, Karttikeya Mangalam, Kurt Keutzer, Michael W. Mahoney, Nicholas Lee, Sehoon Kim, Sheng Shen, Thanakul Wattanawong","submitted_at":"2024-03-22T08:57:07Z","abstract_excerpt":"Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many of them are in the low-data regime, making fine-tuning challenging. To address this, we propose LLM2LLM, a targeted and iterative data augmentation strategy that uses a teacher LLM to enhance a small seed dataset by augmenting additional data that can be used for fine-tuning on a specific task. LLM2LLM (1) fine-tunes a baseline student LLM on the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15042","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/2403.15042/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":"2403.15042","created_at":"2026-07-05T08:43:27.334574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15042v2","created_at":"2026-07-05T08:43:27.334574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15042","created_at":"2026-07-05T08:43:27.334574+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NTYE7PRHYFM","created_at":"2026-07-05T08:43:27.334574+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NTYE7PRHYFMDMDU","created_at":"2026-07-05T08:43:27.334574+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NTYE7PR","created_at":"2026-07-05T08:43:27.334574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.11354","citing_title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5","json":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5.json","graph_json":"https://pith.science/api/pith-number/6NTYE7PRHYFMDMDUBSF4LQJDH5/graph.json","events_json":"https://pith.science/api/pith-number/6NTYE7PRHYFMDMDUBSF4LQJDH5/events.json","paper":"https://pith.science/paper/6NTYE7PR"},"agent_actions":{"view_html":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5","download_json":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5.json","view_paper":"https://pith.science/paper/6NTYE7PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15042&json=true","fetch_graph":"https://pith.science/api/pith-number/6NTYE7PRHYFMDMDUBSF4LQJDH5/graph.json","fetch_events":"https://pith.science/api/pith-number/6NTYE7PRHYFMDMDUBSF4LQJDH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/action/storage_attestation","attest_author":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/action/author_attestation","sign_citation":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/action/citation_signature","submit_replication":"https://pith.science/pith/6NTYE7PRHYFMDMDUBSF4LQJDH5/action/replication_record"}},"created_at":"2026-07-05T08:43:27.334574+00:00","updated_at":"2026-07-05T08:43:27.334574+00:00"}