Scholarlink

<p>This paper evaluates and compares different fine-tuned variations of generative large language models (LLM) in the zero-shot named entity recognition (NER) task for the clinical domain. As part of the 8th Biomedical Linked Annotation Hackathon, we examined <Emphasis FontCategory="NonProportional">Llama 2</Emphasis> and <Emphasis FontCategory="NonProportional">Mistral</Emphasis> models, including base versions and those that have been fine-tuned for code, chat, and instruction-following tasks. We assess both the number of correctly identified entities and the models’ ability to retrieve entities in structured formats. We used a publicly available set of clinical cases labeled with mentions of diseases, symptoms, and medical procedures for the evaluation. Results show that instruction fine-tuned models perform better than chat fine-tuned and base models in recognizing entities. It is also shown that models perform better when simple output structures are requested.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative analysis of generative LLMs for labeling entities in clinical notes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月6日

查看全文
  • Rodrigo del Moral-González,
  • Helena Gómez-Adorno,
  • Orlando Ramos-Flores

摘要

This paper evaluates and compares different fine-tuned variations of generative large language models (LLM) in the zero-shot named entity recognition (NER) task for the clinical domain. As part of the 8th Biomedical Linked Annotation Hackathon, we examined Llama 2 and Mistral models, including base versions and those that have been fine-tuned for code, chat, and instruction-following tasks. We assess both the number of correctly identified entities and the models’ ability to retrieve entities in structured formats. We used a publicly available set of clinical cases labeled with mentions of diseases, symptoms, and medical procedures for the evaluation. Results show that instruction fine-tuned models perform better than chat fine-tuned and base models in recognizing entities. It is also shown that models perform better when simple output structures are requested.