Research map / Large language models / AI and society
Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback
Shijing Zhu, Zhuang Chen, Guanqun Bi, Binghang Li, Yaxi Deng, Dazhen Wan, Libiao Peng, Xiyao Xiao, Rongsheng Zhang, Tangjie Lv, Zhipeng Hu, FangFang Li and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the psycho (counselor role) prompt instead of default system prompt (ablation) | Claude 3.5 Sonnet · Psi-Arena | overall pass rate: 37% -> 84% | Improved |
| add the psycho prompt (ablation) | GPT-3.5 Turbo · Psi-Arena | overall pass rate: 33% -> 39% | Improved |
| add the psycho prompt (ablation) | GPT-4o · Psi-Arena | overall pass rate: 44% -> 57% | Improved |
| add the psycho prompt (ablation) | Deepseek-v3 · Psi-Arena | overall pass rate: 28% -> 65% | Improved |
| closed-loop self-reflection with tripartite feedback | GLM-4-Plus · Psi-Arena | overall pass rate: 39% -> 94% | Improved |
| closed-loop self-reflection feedback | strong models (Claude-3.5-Sonnet) · Psi-Arena | overall pass rate | Mixed |
| closed-loop self-reflection feedback | GPT-3.5 Turbo (weak model) · Psi-Arena | overall pass rate | Mixed |
| simulated client/supervisor/counselor evaluation vs human experts | Psi-Arena auto-eval · Psi-Arena rankings of 4 models | Cohen's kappa: avg 0.733 / 0.696 / 0.685 | Improved |
Closest papers by meaning
- TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots (NeurIPS 2026 · similarity 0.87)
- Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care (ICML 2025 · similarity 0.86)
- An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling (AAAI 2026 · similarity 0.86)
- Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving (ICML 2025 · similarity 0.84)
- CogBench: a large language model walks into a psychology lab (ICML 2024 · similarity 0.84)
- MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
