Research
Current research projects in cognitive modeling and AI for mental health.
Ongoing research
Building and evaluating human-centered AI systems
My current work connects cognitive science, language-model evaluation, and AI-supported mental health.
Towards a Foundation Model for Cognition
On the Use of Foundation Models for Cognitive Science
Naïve Scientific Misconceptions in Large Language Models
Investigating whether and how LLMs internalize intuitive but scientifically incorrect theories, especially when primed with misleading data.
Understanding Graphical Perception in Data Visualization
Extending the arXiv preprint into a formal evaluation suite that compares human visual cognition to vision-language models and develops better prompts for graphs.
Simulating AI Patients for Psychotherapy: Challenges and Opportunities
AI Patient Bank
Building state-based simulated patients grounded in therapeutic source texts and vetted via evidence-based testing.
Collaborators Nathan Paek, William Fang, Hercy Shen, Declan Grabb, Emma Brunskill, Diyi Yang, and Ryan Louie
Ongoing collaboration
Ask Before You Summarize
Clarification-Driven Summaries from Dialogue Transcripts
Admission of uncertainty and clarification elicitations for richer automated summarization.
Collaborators Han-Chin Shing, Lei Xu, Joseph Paul Cohen, Jack Moriarty, and Chaitanya Shivade