← Back to all news
arXiv Computation and Language By Bichen Wang, Yufeng Jin, Yixin Sun, Yanyan Zhao, Bing Qin

When Support Crosses the Line: Evaluating Ethical Boundaries in LLM-Based Mental Health Support in the Chinese Context

Read the original on arXiv Computation and Language →

The paper introduces MindEth-Bench, a benchmark designed to assess whether large language models (LLMs) maintain professional ethical boundaries during multi‑turn mental health interactions in China. It uses Monte Carlo Tree Search to generate challenging dialogue trajectories and evaluates nine LLMs, finding that models can shift from appropriate to unethical responses over time. The study demonstrates that single‑turn tests may overestimate ethical reliability, underscoring the need for comprehensive multi‑turn evaluation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 23

PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling

PsyCLIENT is a framework that uses large language models to simulate counseling clients by conditioning responses on client profiles, dialogue histories, and conversational trajectories that specify target behaviors and content constraints. The authors created PsyCLIENT-CP, a dataset of 120 Chinese client profiles covering 60 counseling topics, and evaluated the system with 24 professional counselors, finding higher authenticity and training utility ratings compared to baseline methods. In a source-identification study, PsyCLIENT-generated dialogues were more often mistaken for real human-client interactions than those from other models, indicating the effectiveness of conversational trajectory modeling in producing realistic counseling conversations.

By Huachuan Qiu, Zhaoming Chen, Yuqian Chen, Yuan Xie, Yu Lu, Zhenzhong Lan
llms
More like this →
arXiv Computation and Language
Oct 23

VEILED-SH: Vulnerability Expression through Indirect Language Evaluation Dataset (Self-Harm)

VEILED‑SH is a new benchmark for evaluating AI responses to indirect expressions of suicide, self‑harm, and distress. It contains 10,003 prompts drawn from counselor chats, forum posts, platform searches, and triage, all grounded in Singaporean contexts and public datasets. The dataset uses an expert‑validated multi‑label taxonomy to classify intent, communicative function, and response behavior, and it includes six automated profiles calibrated to peer‑support practitioners and clinicians for proxy‑alignment scoring.

By Leanne Tan, Keith Chua, Shaun Khoo, Onno P. Kampman, Lim Ruling Charmaine, Hazirah Hoosainsah, Kellie Yu Hui Sim, Kai He, Kenny Tsu Wei Choo, Roy Ka-Wei Lee
benchmarkssafety
More like this →