How large language models handle ethical dilemmas when providing mental health and emotional support

Although generative AI is increasingly used for mental health support, its handling of ethically complex scenarios remains understudied. We evaluated four large language models (GPT-4o, Claude 3.5 Sonnet, Llama 3.3 70B, DeepSeek R1) using the AI Therapeutic Response Scale (AI-TRS). Models achieved moderate performance but showed universal weaknesses in therapeutic insight and boundary management, highlighting critical needs for targeted development and clinical oversight.

Department of Psychological and Brain Sciences, Indiana University Bloomington, Bloomington, IN, USA Department of Neuroscience, University of Minnesota, Minneapolis, MN, USA Department of Counseling Psychology, Santa Clara University, Santa Clara, CA, USA The authors declare no competing interests. Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. Fang, J., Cheng, H., Besada, P. et al. How large language models handle ethical dilemmas when providing mental health and emotional support. npj Mental Health Res (2026). https://doi.org/10.1038/s44184-026-00255-w DOI: https://doi.org/10.1038/s44184-026-00255-w