研究人员开发了BioTool，一个旨在提高大型语言模型利用专业生物医学工具能力的新数据集。该数据集包含来自主要数据库的34个工具，以及超过7000个人工验证的查询-API调用对。在BioTool上对一个40亿参数的LLM进行微调，显著提高了其工具调用性能，在该特定领域甚至超越了GPT-5.1等模型。人工评估证实，这种微调能提高生物医学任务的下游答案质量。 AI
影响 增强LLM在专业生物医学研究和临床应用中的性能。
排序理由 该集群描述了一个新数据集及其在研究论文中的评估。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.05758v1 Announce Type: new Abstract: Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A key limitation is the inability of LLMs to effectively lever…
Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A key limitation is the inability of LLMs to effectively leverage biomedical tools, which clinical experts and…