研究人员开发了AIPatient Arena，一个用于评估临床咨询环境中大语言模型（LLMs）的新框架。该框架使用电子健康记录（EHRs）来模拟真实的、多轮的医患互动。虽然大语言模型在提问技巧、道德行为和解释方面表现出优势，但在信息整合、用药安全、处理歧义、信息覆盖和诊断准确性方面存在不足。 AI
影响 强调了在医疗保健领域对大语言模型进行全面评估的必要性，超越了简单的准确性，侧重于互动和推理。
排序理由 该集群包含一篇学术论文，详细介绍了在特定领域中大语言模型的新评估框架。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.17474v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential,…
Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world c…