arXiv 2603.180082026-02-23cs.CLcs.AIcs.CY

TherapyGym: 评估和对齐疗法聊天机器人中的临床忠实性与安全性

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots

Department of Computer Science, Stanford University, Stanford, CA, USA（计算机科学系，斯坦福大学，斯坦福，加州，美国）；Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA（精神病学与行为科学系，斯坦福大学，斯坦福，加州，美国）；Department of Biomedical Data Science, Stanford University, Stanford, CA, USA（生物医学数据科学系，斯坦福大学，斯坦福，加州，美国）；University of California, Berkeley, Berkeley, CA, USA（加州大学伯克利分校，伯克利，加州，美国）；The University of Hong Kong, Hong Kong（香港大学，香港）

Fangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang, Sijun Tan, Kenan Ye, Lily Bailey, Merryn Daniel, Ryan Louie, Sanmi Koyejo, Ehsan Adeli

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

TherapyGym通过评估和提升疗法聊天机器人中的忠实性与安全性，结合CTRS评分和多标签标注方案，利用RL训练框架改进模型性能，提升临床应用的安全性和有效性。

摘要：

大型语言模型（LLMs）越来越多地用于心理健康支持；然而，现有的评估方法——流畅性指标、偏好测试和通用对话基准——无法捕捉心理治疗中至关重要的临床维度。我们引入THERAPYGYM框架，评估和改进疗法聊天机器人沿两个临床支柱：忠实性和安全性。忠实性通过认知治疗评分量表（CTRS）测量，实现为自动化流程，评分在多轮对话中遵循CBT技术的符合程度。安全性通过多标签标注方案评估，涵盖治疗特定风险（例如未能处理伤害或虐待）。为减轻LLM基于判断者的偏见和不可靠性，我们进一步发布了THERAPYJUDGEBENCH，包含116个对话和1,270个专家评分的验证集，用于审计和校准以对抗受过许可的临床专家。THERAPYGYM还充当训练框架：CTRS和安全性基于奖励驱动RL，具有可配置的患者模拟，涵盖多样化的症状概况。在THERAPYGYM训练的模型在专家评分上有所提升，平均CTRS从0.10提高到0.60（在LLM判断者下为0.16到0.59）。我们的工作使可扩展开发出忠实于循证实践且在高风险使用中更安全的疗法聊天机器人成为可能。

英文摘要：

Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks--fail to capture the clinically critical dimensions of psychotherapy. We introduce THERAPYGYM, a framework that evaluates and improves therapy chatbots along two clinical pillars: fidelity and safety. Fidelity is measured using the Cognitive Therapy Rating Scale (CTRS), implemented as an automated pipeline that scores adherence to CBT techniques over multi-turn sessions. Safety is assessed using a multi-label annotation scheme, covering therapy-specific risks (e.g., failing to address harm or abuse). To mitigate bias and unreliability in LLM-based judges, we further release THERAPYJUDGEBENCH, a validation set of 116 dialogues with 1,270 expert ratings for auditing and calibration against licensed clinicians. THERAPYGYM also serves as a training harness: CTRS and safety-based rewards drive RL with configurable patient simulations spanning diverse symptom profiles. Models trained in THERAPYGYM improve on expert ratings, with average CTRS rising from 0.10 to 0.60 (and 0.16 to 0.59 under LLM judges). Our work enables scalable development of therapy chatbots that are faithful to evidence-based practice and safer in high-stakes use.

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。