{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7F6YUYVR2MFXWKY7OW7PBWGBNY","short_pith_number":"pith:7F6YUYVR","schema_version":"1.0","canonical_sha256":"f97d8a62b1d30b7b2b1f75bef0d8c16e1aded1d705b61b64d5d3aff38e1b9014","source":{"kind":"arxiv","id":"2404.00152","version":2},"attestation_state":"computed","paper":{"title":"On-the-fly Definition Augmentation of LLMs for Biomedical NER","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakanksha Naik, Byron C Wallace, Monica Munnangi, Sergey Feldman, Silvio Amir, Tom Hope","submitted_at":"2024-03-29T20:59:27Z","abstract_excerpt":"Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out to improve LLM performance on biomedical NER in limited data settings via a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly. During this process, to provide a test bed for knowledge augmentation, we perform a comprehensive exploration of prompting strategies. Our experiments show that definition augmentation is useful for both open source and close"},"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":"2404.00152","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T20:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"c07a5005058a4cb51aa7c40e2f60388f712e6823393ad20e237d630199f41a2a","abstract_canon_sha256":"4047be926789b8245c8a0f96f10d2f960600f67f9303efb4e5015a341ebb1ece"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:02.869288Z","signature_b64":"yoslGqLTV+4T0jce2Jp0Fb64gSMgXtVdUu6oYOGarMYd/2qc9zX/Vc09epgsAtvoJpRczMVZiiHApR0ID/NdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f97d8a62b1d30b7b2b1f75bef0d8c16e1aded1d705b61b64d5d3aff38e1b9014","last_reissued_at":"2026-07-05T08:11:02.868945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:02.868945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-the-fly Definition Augmentation of LLMs for Biomedical NER","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakanksha Naik, Byron C Wallace, Monica Munnangi, Sergey Feldman, Silvio Amir, Tom Hope","submitted_at":"2024-03-29T20:59:27Z","abstract_excerpt":"Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out to improve LLM performance on biomedical NER in limited data settings via a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly. During this process, to provide a test bed for knowledge augmentation, we perform a comprehensive exploration of prompting strategies. Our experiments show that definition augmentation is useful for both open source and close"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00152","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/2404.00152/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":"2404.00152","created_at":"2026-07-05T08:11:02.869000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00152v2","created_at":"2026-07-05T08:11:02.869000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00152","created_at":"2026-07-05T08:11:02.869000+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F6YUYVR2MFX","created_at":"2026-07-05T08:11:02.869000+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F6YUYVR2MFXWKY7","created_at":"2026-07-05T08:11:02.869000+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F6YUYVR","created_at":"2026-07-05T08:11:02.869000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11779","citing_title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY","json":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY.json","graph_json":"https://pith.science/api/pith-number/7F6YUYVR2MFXWKY7OW7PBWGBNY/graph.json","events_json":"https://pith.science/api/pith-number/7F6YUYVR2MFXWKY7OW7PBWGBNY/events.json","paper":"https://pith.science/paper/7F6YUYVR"},"agent_actions":{"view_html":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY","download_json":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY.json","view_paper":"https://pith.science/paper/7F6YUYVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00152&json=true","fetch_graph":"https://pith.science/api/pith-number/7F6YUYVR2MFXWKY7OW7PBWGBNY/graph.json","fetch_events":"https://pith.science/api/pith-number/7F6YUYVR2MFXWKY7OW7PBWGBNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY/action/storage_attestation","attest_author":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY/action/author_attestation","sign_citation":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY/action/citation_signature","submit_replication":"https://pith.science/pith/7F6YUYVR2MFXWKY7OW7PBWGBNY/action/replication_record"}},"created_at":"2026-07-05T08:11:02.869000+00:00","updated_at":"2026-07-05T08:11:02.869000+00:00"}