用提示工程+合成数据，让大模型在法语医疗文本中精准识别实体和事件。
LLM, Reporting In! Medical Information Extraction Across Prompting, Fine-tuning and Post-correction
- 用GPT-4.1结合精选示例与标注指南做少样本提示学习
- 在法语医疗数据上达61.53%宏平均F1，事件抽取15.02%
- 适合低资源语言医疗信息提取任务的快速部署
本文参与了EvalLLM 2025挑战赛中法语生物医学命名实体识别（NER）与健康事件抽取任务（少样本设置）。针对NER，提出三种融合大语言模型（LLMs）、标注指南、合成数据与后处理的方法：(1) 使用GPT-4.1进行上下文学习（ICL），自动选取10个示例并整合标注指南摘要至提示；(2) 通用NER系统GLiNER，在合成语料上微调后由大模型进行后处理验证；(3) 开源模型LLaMA-3.1-8B-Instruct，在相同合成语料上微调。事件抽取采用与NER相同的GPT-4.1 ICL策略，复用指南摘要。结果表明，GPT-4.1在NER上取得61.53%宏平均F1，事件抽取为15.02%，凸显精心设计提示在极低资源场景中的关键作用。
原文摘要 · Abstract (English)
This work presents our participation in the EvalLLM 2025 challenge on biomedical Named Entity Recognition (NER) and health event extraction in French (few-shot setting). For NER, we propose three approaches combining large language models (LLMs), annotation guidelines, synthetic data, and post-processing: (1) in-context learning (ICL) with GPT-4.1, incorporating automatic selection of 10 examples and a summary of the annotation guidelines into the prompt, (2) the universal NER system GLiNER, fine-tuned on a synthetic corpus and then verified by an LLM in post-processing, and (3) the open LLM LLaMA-3.1-8B-Instruct, fine-tuned on the same synthetic corpus. Event extraction uses the same ICL strategy with GPT-4.1, reusing the guideline summary in the prompt. Results show GPT-4.1 leads with a macro-F1 of 61.53% for NER and 15.02% for event extraction, highlighting the importance of well-crafted prompting to maximize performance in very low-resource scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。