PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism and Comprehensive AI Psychological Counselor
By: Wei Wang, Chenxu Wang, Guohao Li, Guojun Wu, Yutong Lu, Xiang Zhou, Zhaoting Li, Shizhong Liu
Published: 2026-01-06
View on arXiv →#cs.AI
Abstract
This paper proposes PsychEval, a new multi-session and multi-therapy benchmark for evaluating AI psychological counselors. It aims to provide high-realism and comprehensive assessment of AI's capabilities in providing psychological support, pushing the boundaries of responsible AI development in sensitive fields. The benchmark addresses the need for robust evaluation tools for AI in mental health, a domain with significant real-world implications.