Research
Mission
We design, develop, and study human-centered AI systems that help people understand system behavior, interact with it effectively, and use it responsibly. Our research lab aims to create AI technologies that are both technically reliable and socially beneficial.
Topics of Interest
- LLM-based Evaluation: Designing human-in-the-loop LLM-based evaluation methods and tools that help practitioners assess the quality of data. (View related project)
- AI Hallucination: Studying how AI-generated information can be presented in ways that help users understand uncertainty/factuality and calibrate their trust. (View related project)
- Agent Design and Governance: Exploring mechanisms for designing and governing AI agents, including oversight, transparency, and human control over agentic systems and their actions. (View related project)
- Conversational Interaction: Designing conversational assistants and interfaces that improve communication, collaboration, and user understanding. (View related project)
- AI Disclosure: Investigating how the use of AI should be communicated in human–AI co-created and AI-assisted work, and how ownership and accountability should be defined. (View related project)
- And More: We are also open to related ideas and collaborations beyond the topics listed above.
Student Opportunities
If you are interested in joining or collaborating on projects, please send a short email describing:
- your background, relevant coursework, or experience
- what you are looking for (e.g., research assistantship, capstone project, independent study)
- the research area you are interested in, if any
Coming Soon
Our research group page is still under development and will be launched soon as the lab takes shape. In the meantime, please visit this page for the latest updates on our research. Stay tuned!