Publication
Deceptive explanations by large language models lead people to change their beliefs about misinformation more often than honest explanations
Danry, V., Pataranutaporn, P., Groh, M., & Epstein, Z. (2025, April). Deceptive explanations by large language models lead people to change their beliefs about misinformation more often than honest explanations. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (pp. 1-31).
Publication
Deceptive AI systems that give explanations are just as convincing as honest AI systems in human-machine decision making
Danry, Valdemar, Pat Pataranutaporn, Ziv Epstein, Matthew Groh, and Pattie Maes (Under review). “Deceptive AI systems that give explanations are just as convincing as honest AI systems in human-machine decision making.” Extended Abstract. Presented at the International Conference on Computational Social Science (IC2S2) 2022.