MedARC:适应性多代理精细化和协作,以在大型语言模型中增强医学推理
Yongming Miao1, Jiaxin Wen2, Yuemei Luo1
1School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China; Jiangsu Key Laboratory of Intelligent Medical Image Computing, Nanjing University of Information Science and Technology, Nanjing, China.
International journal of medical informatics
|October 18, 2025
概括
MedARC是一个新的多代理框架,通过在大型语言模型 (LLM) 之间进行结构化辩论来增强医疗问题答案. 这种方法提高了复杂的生物医学信息任务的准确性和可靠性.
科学领域:
- 人工智能的人工智能
- 生物医学信息学 生物医学信息学
- 自然语言处理自然语言处理.
背景情况:
- 大型语言模型 (LLM) 在医学问题答案 (QA) 中表现有前途.
- 临床部署受到LLM限制的阻碍,例如幻觉和不一致的推理.
- 处理复杂的生物医学信息仍然是当前LLMs的一个挑战.
研究的目的:
- 引入MedARC (医疗剂精制和协作),这是一个多剂框架,用于增强医疗质量保证.
- 通过结构化的代理人间辩论,解决医疗质量保证中LLM的局限性.
- 提高LLM产生的医学答案的事实一致性,完整性和可靠性.
主要方法:
- MedARC采用多代理框架,在LLM代理人之间进行结构化的辩论.
- 关键机制包括结构化的代理人间总结,以改进协议/分歧.
- 自信意识聚合从可靠的代理贡献中合成最终答案.
主要成果:
- 与零射击和Cot基线相比,MedARC显著提高了医疗质量保证基准的表现.
- 在使用DeepSeek-V3.3的PubMedQA上,精度从72.9%增加到77.2%.
- 人类评估证实了MedARC的增强的事实一致性和完整性.
结论:
- MedARC为基于LLM的医疗QA提供了一个可靠和可扩展的解决方案.
- 该框架有效地解决了临床环境中的LLM限制.
- 开源代码可用于进一步的研究和开发.
相关概念视频
Methods of Documentation VI: Case Management Model
829
The case management model is a multidisciplinary approach that involves healthcare professionals from diverse disciplines, such as physicians, nurses, therapists, social workers, and pharmacists, working collaboratively to address the various needs of patients. Each healthcare professional brings unique expertise and perspectives, contributing to a more comprehensive understanding of the patient's condition and tailoring treatment plans accordingly.
For example, a patient with a chronic...
For example, a patient with a chronic...
829
Improving Translational Accuracy
14.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.0K
Improving Translational Accuracy
3.5K
3.5K

