Human-AI Interaction

Examining how people interact with AI systems and how to build safer ones.

AI on the ground Health Human-AI Interaction Participatory methods Privacy & Data Access Science of Evaluations

2026

Reliability of LLMs as medical assistants for the general public: a randomized preregistered study

Published in Nature Medicine

Training language models to be warm can reduce accuracy and increase sycophancy

Published in Nature

2025

Supporting adolescents to challenge algorithmic profiling in online platforms

Preprint on arXiv

Evaluating the use of a language model to crowdsource gun violence reports

Presented at ACM CSCW