arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.05671cs.CL
收藏

ClinTutor-R1:在临床苏格拉底式教育中推进可扩展且稳健的一对多对齐

ClinTutor-R1: Advancing Scalable and Robust One-to-Many Alignment in Clinical Socratic Education

Hong Kong University of Science and Technology(香港理工大学)

Zhitao He, Haolin Yang, Zeyu Qin, Yi R Fung

AI总结:

针对临床查房等一对多教学场景中上下文稀释与目标错位问题,提出基于多智能体模拟器ClinEdu构建的苏格拉底式教学数据集ClinTeach,并开发首个显式内部思维机制的一对多对齐视觉语言智能体ClinTutor-R1,通过建模个体信念状态与群体共识,在静态基准、交互评估、专家评审及200人真实用户研究中超越基线模型20%以上,达到与专有模型相当的性能,并展现出随学生规模扩展的教学质量可扩展性。

摘要:

尽管大型语言模型(LLMs)在二元(一对一)教学中取得了显著成功,但在临床查房等一对多对齐场景中面临重大挑战,此时教师必须同时指导一群多样化的受训者。当前模型常受上下文稀释与目标错位影响,难以平衡个体脚手架与集体学习进度。为此,我们引入ClinEdu,一个模拟群体动态复杂性的多智能体教学模拟器。基于该平台,我们构建了ClinTeach,一个大规模的苏格拉底式教学对话数据集,并提出ClinTutor-R1,这是首个明确设计用于实现临床教育中一对多对齐的视觉语言智能体,采用显式内部思维机制来建模个体信念状态与群体共识。我们通过涵盖静态基准、ClinEdu内原位交互评估、专家评估以及200名参与者的真实用户研究的综合协议验证了我们的框架。实验结果表明,ClinTutor-R1在性能上超越基线模型超过20%,并达到与专有模型相当的水平,同时在扩展学生群体时展现出维持教学质量的扩展性。

英文摘要:

While Large Language Models (LLMs) have achieved remarkable success in dyadic (one-on-one) instruction, they face significant challenges in One-to-Many alignment, such as clinical ward rounds, where an instructor must simultaneously guide a diverse group of trainees. Current models often suffer from context dilution and goal misalignment, failing to balance individual scaffolding with collective learning progress. To address this, we introduce ClinEdu, a multi-agent pedagogical simulator that models the complexity of group dynamics. Leveraging this platform, we construct ClinTeach, a large-scale dataset of Socratic teaching dialogues, and propose ClinTutor-R1, the first vision-language agent explicitly architected to achieve one-to-many alignment in clinical education, employing an explicit internal thinking mechanism to model both individual belief states and group consensus. We validate our framework through a comprehensive protocol covering static benchmarks, in-situ interactive evaluation within ClinEdu, expert assessment, and a 200-participant real user study. Experimental results demonstrate that ClinTutor-R1 outperforms base models by over 20% and achieves parity with proprietary models, while exhibiting scalability in maintaining instructional quality across expanding student cohorts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑