{"ID":2850301,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22285","arxiv_id":"2510.22285","title":"Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER","abstract":"We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL) under simple vs.\\ complex prompts, and (iii) GPT-4o with supervised fine-tuning (SFT). All models are evaluated on standard NER metrics over CADEC's five entity types (ADR, Drug, Disease, Symptom, Finding). RoBERTa-large and BioClinicalBERT offer limited improvements over BERT Base, showing the limit of these family of models. Among LLM settings, simple ICL outperforms a longer, instruction-heavy prompt, and SFT achieves the strongest overall performance (F1 $\\approx$ 87.1%), albeit with higher cost. We find that the LLM achieve higher accuracy on simplified tasks, restricting classification to two labels.","short_abstract":"We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL) under simple vs.\\ complex prompts, and (iii) GPT-4o with supervised fine-tuning (SF...","url_abs":"https://arxiv.org/abs/2510.22285","url_pdf":"https://arxiv.org/pdf/2510.22285v1","authors":"[\"Andrei Baroian\"]","published":"2025-10-25T13:08:59Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}