Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling
The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive responses may inadvertently reinforce harmful beliefs or behaviors in multi-turn conversations. This risk is largely overlooked by existing red-teaming frameworks, which focus mainly on generic harms or optimization-based attacks. To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose vu...
| Authors | Qingyang Xu, Yaling Shen, Stephanie Fong et al. |
|---|---|
| Primary category | cs.CL |
| Published | 6 April 2026 |
| Last updated at source | 5 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.