AI–Human Interaction

As conversational AI enters mental health care, we examine how people interact with it. We test whether language model responses are perceived as empathic and supportive, analyze tens of thousands of real conversations between users and AI to characterize safety-relevant behavior, and study engagement and outcomes when generative AI is deployed for social and mental health support. We also build adversarial user simulations that expose how systems fail, so that these interactions can be evaluated and improved before and during deployment.

Selected Publications

Wolfe, E. C., Su, T., Tieleman, O., Hull, T. D., Malgaroli, M., Stamatis, C. A. (2026). Engagement phenotypes for a sample of 102,684 AI mental health chatbot users and dose-response associations with clinical outcomes. arXiv preprint.

Language ModelsHuman–AIComputationalDigital Health

Stamatis, C. A., Wolfe, E. C., Malgaroli, M., Hull, T. D. (2026). Talking to a human as an attitudinal barrier: A mixed methods evaluation of stigma, access, and the appeal of AI mental health support. arXiv preprint.

Human–AIDigital Health

Stamatis, C. A., Meyerhoff, J., Zhang, R., Tieleman, O., Malgaroli, M., Hull, T. D. (2026). Beyond simulations: What 20,000 real conversations reveal about mental health AI safety. arXiv preprint.

Language ModelsHuman–AI

Hull, T. D., Zhang, L., Arean, P. A., Malgaroli, M. (2025). Generative AI purpose-built for social and mental health: A real-world pilot. arXiv preprint.

Language ModelsHuman–AIDigital Health

Zhu, Z., Tieleman, O., Stamatis, C. A., Smyth, L., Hull, T. D., Cahn, D. R., Chen, J., Malgaroli, M. (2026). DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP).

NLP & Language MarkersLanguage ModelsHuman–AI

Gabriel, S., Puri, I., Xu, X., Malgaroli, M., Ghassemi, M. (2024). Can AI relate: Testing large language model response for mental health support. Findings of the Association for Computational Linguistics: EMNLP 2024.

NLP & Language MarkersLanguage ModelsHuman–AIComputational

See all publications →