{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QGCW2YP4R5R2UQFVISDYAGC343","short_pith_number":"pith:QGCW2YP4","schema_version":"1.0","canonical_sha256":"81856d61fc8f63aa40b5448780185be6f80f3735401cfd3360216ccbd630080b","source":{"kind":"arxiv","id":"2403.02271","version":2},"attestation_state":"computed","paper":{"title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alona Fyshe, Saeed Najafi","submitted_at":"2024-03-04T17:58:09Z","abstract_excerpt":"Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number of model parameters (e.g LoRA). In this study, we explore the impact of altering the input text of the original task in conjunction with parameter-efficient fine-tuning methods. To most effectively rewrite the input text, we train a few-shot paraphrase model with a Maximum-Marginal Likelihood objective. Using six few-shot text classification datasets, we sh"},"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":"2403.02271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T17:58:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b7b9269e64531e0e1f7ab16c2e4305536f36bb69d14f2d8c0e0f08a61d4fab1","abstract_canon_sha256":"75dcba0f41e909a935a60f8a9b2e3a937c6bcc9859e3cdff23f4b2e8b2dd97e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:07.417974Z","signature_b64":"I/bjzr8s3w9P58g1pVK/eaGa5TU+hY1TGUex67YRzTmIOa7j5qyOm7judtar1H2+Ml8746SyK+1prxMLPHCxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81856d61fc8f63aa40b5448780185be6f80f3735401cfd3360216ccbd630080b","last_reissued_at":"2026-07-05T08:28:07.417504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:07.417504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alona Fyshe, Saeed Najafi","submitted_at":"2024-03-04T17:58:09Z","abstract_excerpt":"Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number of model parameters (e.g LoRA). In this study, we explore the impact of altering the input text of the original task in conjunction with parameter-efficient fine-tuning methods. To most effectively rewrite the input text, we train a few-shot paraphrase model with a Maximum-Marginal Likelihood objective. Using six few-shot text classification datasets, we sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02271","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/2403.02271/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":"2403.02271","created_at":"2026-07-05T08:28:07.417563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02271v2","created_at":"2026-07-05T08:28:07.417563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02271","created_at":"2026-07-05T08:28:07.417563+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGCW2YP4R5R2","created_at":"2026-07-05T08:28:07.417563+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGCW2YP4R5R2UQFV","created_at":"2026-07-05T08:28:07.417563+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGCW2YP4","created_at":"2026-07-05T08:28:07.417563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07280","citing_title":"From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343","json":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343.json","graph_json":"https://pith.science/api/pith-number/QGCW2YP4R5R2UQFVISDYAGC343/graph.json","events_json":"https://pith.science/api/pith-number/QGCW2YP4R5R2UQFVISDYAGC343/events.json","paper":"https://pith.science/paper/QGCW2YP4"},"agent_actions":{"view_html":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343","download_json":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343.json","view_paper":"https://pith.science/paper/QGCW2YP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/QGCW2YP4R5R2UQFVISDYAGC343/graph.json","fetch_events":"https://pith.science/api/pith-number/QGCW2YP4R5R2UQFVISDYAGC343/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343/action/storage_attestation","attest_author":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343/action/author_attestation","sign_citation":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343/action/citation_signature","submit_replication":"https://pith.science/pith/QGCW2YP4R5R2UQFVISDYAGC343/action/replication_record"}},"created_at":"2026-07-05T08:28:07.417563+00:00","updated_at":"2026-07-05T08:28:07.417563+00:00"}