The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
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.
arXiv:2603. 00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making.
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.
APRiL is an open‑ended benchmark designed to evaluate Chinese large language models’ social awareness. It comprises 2,196 evaluation instances across six categories, split into two tasks: Social Scenario Analysis, which tests understanding of social cues, mental states, and conflict structures, and Socially Aware Response, which checks whether models can generate appropriate, natural replies. Experiments on twelve models from six families show a consistent gap between understanding and response quality, indicating that stronger scenario analyses tend to improve response performance.
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.
arXiv:2607. 10871v1 Announce Type: new Abstract: Contemplative traditions have long guided ethical behavior and prosocial interaction, and recent work suggests that contemplative principles (e.