Papers
Working Papers
Hewitt, L.*, Ashokkumar, A*., Ghezae, I., & Willer, R. Predicting Results of Social Science Experiments Using Large Language Models. Supplementary Materials.
Web demo, Thread: LLM Predictions, Talk at Stanford Tech Impact and Policy Center, Talk at HAI (09/2023)
Media Coverage: HAI (07/25)
Park, J. S., Zou, C. Q., Shaw, A., Hill, B. M., Cai, C., Morris, M. R., Willer, R., Liang, P., & Bernstein, M. S. Generative Agent Simulations of 1,000 People. Working Paper.
Media Coverage: ScienceDirect (11/24)
Mernyk, J. S., Kamphorst, J. B., Sivakumar, K., Bonica, A., Willer, R. A nonpartisan source-grounded AI voter guide is perceived as trustworthy and affects voting intentions.
Schöne , J. P., Salecha, A., Lyubomirsky, S., Eichstaedt, J., & Willer, R. Structured AI Dialogues Can Increase Happiness and Meaning in Life.
Costello, T.H., Pennycook, G., Willer, R., & Rand, D. Deep Canvassing using AI reduces prejudice toward undocumented immigrants.
Jackson, M. O., Mei, Q., Wang, S., Xie, Y., Yuan, W., Benzell, S. G., Brynjolfsson, E., Camerer, C. F., Evans, J. A., Jabarian, B., Kleinberg, J., Meng, J., Mullainathan, S., Ozdaglar, A. E., Pfeiffer, T., Tennenholtz, M., Willer, R., Yang, D., & Ye, T. AI Behavioral Science.
2026 / In Press
Gallegos, I. O., Shani, C., Shi, W., Bianchi, F., Gainsburg, I., Jurafsky, D., & Willer, R. In Press. Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects. PNAS Nexus.
2025
Bai, H., Voelkel, J. G., Muldowney, S., Eichstaedt, J. C., & Willer, R. 2025. LLM-Generated Messages Can Persuade Humans on Policy Issues. Nature Communications.
Press Release: AI Persuasion, Thread: LLMs & Changing Attitudes
Media Coverage: Stanford Report (12/25)
2024
Stade, E. C., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., Sedoc, J., DeRubeis, R. J., Willer, R. & Eichstaedt, J. C. 2024. Large Language Models Could Change the Future of Behavioral Healthcare: A Proposal for Responsible Development and Evaluation. NPJ Mental Health Research.