Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2026

Abstract

Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and context-dependent nature of clinical harm. Existing evaluation frameworks predominantly assess isolated responses using coarse-grained taxonomies or static datasets, limiting their ability to diagnose how harms emerge and accumulate over multi-turn counseling interactions. In this work, we introduce R-MHSafe, a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of the interactional roles an AI counselor adopts, including perpetrator, instigator, facilitator, or enabler, combined with clinically grounded harm categories. Then, we propose MHSafeEval, a closed-loop, agent-based evaluation framework that formulates safety assessment as trajectory-level discovery of harm through adversarial multi-turn interactions, guided by role-aware modeling. Using R-MHSafe and MHSafeEval, we conduct a large-scale evaluation across state-of-the-art LLMs. Our results reveal substantial role-dependent and cumulative safety failures that are systematically missed by existing static benchmarks, and show that our framework significantly improves failure-mode coverage and diagnostic granularity.

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, California, July 2-7

First Page

27760

Last Page

27793

Identifier

10.18653/v1/2026.findings-acl.1382

Publisher

ACL

City or Country

USA

Additional URL

https://doi.org/10.18653/v1/2026.findings-acl.1382

Download

Share

COinS