Computational Cognitive Science Lab

Home | Research | People | Publications | Resources

By Bai, X.
SML	Ku, A., Campbell, D., Bai, X., Geng, J., Liu, R., Marjieh, R., McCoy, R. T., Nam, A., Sucholutsky, I., Veselovsky, V., Zhang, L., Zhu, J. Q., & Griffiths, T. L. (2026). Levels of analysis for large language models. Philosophical Transactions of the Royal Society A, 384(2320). (pdf)
DMRL SC SML	Wu, A. J., Liu, R., Bai, X., & Griffiths, T. L. (2025). Large language models develop novel social biases through adaptive exploration. Proceedings of the Fourty-third International Conference on Machine Learning (ICML). (pdf)
PR SML	Bai, X., Wang, A., Sucholutsky, I., & Griffiths, T. L. (2025). Explicitly unbiased large language models still form biased associations. Proceedings of the National Academy of Sciences, 122(8), e2416228122. (pdf)
DMRL SC	Bai, X., Griffiths, T. L., & Fiske, S. T. (2024). Costly exploration produces stereotypes with dimensions of warmth and competence. Journal of Experimental Psychology: General. (pdf)
SC SML	Bai, X., Wang, A., Sucholutsky, I., & Griffiths, T. L. (2024). Measuring implicit bias in explicitly unbiased large language models. (preprint)
DMRL SC	Bai, X., Fiske, S. T., & Griffiths, T. L. (2022). Globally inaccurate stereotypes can result from locally adaptive exploration. Psychological Science, 33(5) 671–684. (pdf)