{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ARI72DISEEFBJSDLGVIYNTFRO3","short_pith_number":"pith:ARI72DIS","schema_version":"1.0","canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","source":{"kind":"arxiv","id":"2012.15723","version":2},"attestation_state":"computed","paper":{"title":"Making Pre-trained Language Models Better Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Danqi Chen, Tianyu Gao","submitted_at":"2020-12-31T17:21:26Z","abstract_excerpt":"The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together"},"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":"2012.15723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T17:21:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bec6d4a59628c1657fd8400e7274ced39284cc92085e4ef1fcda3dd597253f56","abstract_canon_sha256":"ea0c0e76c41a38909394828d1febacbbcce18ba173b8afedbb2c4b38f5f2065b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:35.589817Z","signature_b64":"j3pIWh0CjMq0oecm7rHbHZxTsu0Y7GH6f80ScQ9U4TrLyiizPZ+X1ggT7Ob0etceaBRymHjR7L8fa9H5qHzRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0451fd0d12210a14c86b355186ccb176c863b8cd42415d28aea5cbfe93c0f54c","last_reissued_at":"2026-07-05T02:45:35.589377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:35.589377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Pre-trained Language Models Better Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Danqi Chen, Tianyu Gao","submitted_at":"2020-12-31T17:21:26Z","abstract_excerpt":"The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15723","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/2012.15723/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":"2012.15723","created_at":"2026-07-05T02:45:35.589432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15723v2","created_at":"2026-07-05T02:45:35.589432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15723","created_at":"2026-07-05T02:45:35.589432+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARI72DISEEFB","created_at":"2026-07-05T02:45:35.589432+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARI72DISEEFBJSDL","created_at":"2026-07-05T02:45:35.589432+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARI72DIS","created_at":"2026-07-05T02:45:35.589432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17637","citing_title":"Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30775","citing_title":"A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2211.16327","citing_title":"On the Power of Foundation Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08812","citing_title":"Test-Time Alignment via Hypothesis Reweighting","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11362","citing_title":"On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2309.02427","citing_title":"Cognitive Architectures for Language Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03409","citing_title":"Large Language Models as Optimizers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2304.03442","citing_title":"Generative Agents: Interactive Simulacra of Human Behavior","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05732","citing_title":"Graph Topology Information Enhanced Heterogeneous Graph Representation Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3","json":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3.json","graph_json":"https://pith.science/api/pith-number/ARI72DISEEFBJSDLGVIYNTFRO3/graph.json","events_json":"https://pith.science/api/pith-number/ARI72DISEEFBJSDLGVIYNTFRO3/events.json","paper":"https://pith.science/paper/ARI72DIS"},"agent_actions":{"view_html":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3","download_json":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3.json","view_paper":"https://pith.science/paper/ARI72DIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15723&json=true","fetch_graph":"https://pith.science/api/pith-number/ARI72DISEEFBJSDLGVIYNTFRO3/graph.json","fetch_events":"https://pith.science/api/pith-number/ARI72DISEEFBJSDLGVIYNTFRO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/action/storage_attestation","attest_author":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/action/author_attestation","sign_citation":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/action/citation_signature","submit_replication":"https://pith.science/pith/ARI72DISEEFBJSDLGVIYNTFRO3/action/replication_record"}},"created_at":"2026-07-05T02:45:35.589432+00:00","updated_at":"2026-07-05T02:45:35.589432+00:00"}