Saved in:
Bibliographic Details
Main Authors: Lee, Suhyun, Achananuparp, Palakorn, Yadav, Neemesh, Lim, Ee-Peng, Deng, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.17730
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913046037790720
author Lee, Suhyun
Achananuparp, Palakorn
Yadav, Neemesh
Lim, Ee-Peng
Deng, Yang
author_facet Lee, Suhyun
Achananuparp, Palakorn
Yadav, Neemesh
Lim, Ee-Peng
Deng, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17730
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
Lee, Suhyun
Achananuparp, Palakorn
Yadav, Neemesh
Lim, Ee-Peng
Deng, Yang
Computation and Language
Artificial Intelligence
Human-Computer Interaction
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.
title MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2604.17730