{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AW2VG3ZQSWGTPNG6N54Q5RGHTM","short_pith_number":"pith:AW2VG3ZQ","schema_version":"1.0","canonical_sha256":"05b5536f30958d37b4de6f790ec4c79b35deac9a95eea12a62aa27a18e075d7c","source":{"kind":"arxiv","id":"2508.06504","version":1},"attestation_state":"computed","paper":{"title":"Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abeed Sarker, Sudeshna Das, Yao Ge, Yuting Guo","submitted_at":"2025-07-25T20:57:16Z","abstract_excerpt":"Biomedical named entity recognition (NER) is a high-utility natural language processing (NLP) task, and large language models (LLMs) show promise particularly in few-shot settings (i.e., limited training data). In this article, we address the performance challenges of LLMs for few-shot biomedical NER by investigating a dynamic prompting strategy involving retrieval-augmented generation (RAG). In our approach, the annotated in-context learning examples are selected based on their similarities with the input texts, and the prompt is dynamically updated for each instance during inference. We impl"},"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":"2508.06504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T20:57:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d89fc72710957a4785c37dee16a54860c8cbfc4320257fdea049f786cecbea4f","abstract_canon_sha256":"16ca985a62d3af9699811ba8ade2a3015b02c067097a05a166b9b652bc341aa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:00.711822Z","signature_b64":"32x2pW2qRHIegHXj0hxNHa5E7JJvtJLQoFyt83Xv/6FOV8lmGISYWoXdDSYUET3i5P944Jc5HOCLCB6gegOSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05b5536f30958d37b4de6f790ec4c79b35deac9a95eea12a62aa27a18e075d7c","last_reissued_at":"2026-07-05T11:51:00.710997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:00.710997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval augmented generation based dynamic prompting for few-shot biomedical named entity recognition using large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abeed Sarker, Sudeshna Das, Yao Ge, Yuting Guo","submitted_at":"2025-07-25T20:57:16Z","abstract_excerpt":"Biomedical named entity recognition (NER) is a high-utility natural language processing (NLP) task, and large language models (LLMs) show promise particularly in few-shot settings (i.e., limited training data). In this article, we address the performance challenges of LLMs for few-shot biomedical NER by investigating a dynamic prompting strategy involving retrieval-augmented generation (RAG). In our approach, the annotated in-context learning examples are selected based on their similarities with the input texts, and the prompt is dynamically updated for each instance during inference. We impl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06504","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/2508.06504/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":"2508.06504","created_at":"2026-07-05T11:51:00.711103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06504v1","created_at":"2026-07-05T11:51:00.711103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06504","created_at":"2026-07-05T11:51:00.711103+00:00"},{"alias_kind":"pith_short_12","alias_value":"AW2VG3ZQSWGT","created_at":"2026-07-05T11:51:00.711103+00:00"},{"alias_kind":"pith_short_16","alias_value":"AW2VG3ZQSWGTPNG6","created_at":"2026-07-05T11:51:00.711103+00:00"},{"alias_kind":"pith_short_8","alias_value":"AW2VG3ZQ","created_at":"2026-07-05T11:51:00.711103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM","json":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM.json","graph_json":"https://pith.science/api/pith-number/AW2VG3ZQSWGTPNG6N54Q5RGHTM/graph.json","events_json":"https://pith.science/api/pith-number/AW2VG3ZQSWGTPNG6N54Q5RGHTM/events.json","paper":"https://pith.science/paper/AW2VG3ZQ"},"agent_actions":{"view_html":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM","download_json":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM.json","view_paper":"https://pith.science/paper/AW2VG3ZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06504&json=true","fetch_graph":"https://pith.science/api/pith-number/AW2VG3ZQSWGTPNG6N54Q5RGHTM/graph.json","fetch_events":"https://pith.science/api/pith-number/AW2VG3ZQSWGTPNG6N54Q5RGHTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM/action/storage_attestation","attest_author":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM/action/author_attestation","sign_citation":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM/action/citation_signature","submit_replication":"https://pith.science/pith/AW2VG3ZQSWGTPNG6N54Q5RGHTM/action/replication_record"}},"created_at":"2026-07-05T11:51:00.711103+00:00","updated_at":"2026-07-05T11:51:00.711103+00:00"}