I am a fourth-year Ph.D. student at the Computer Science Department of University of Maryland, College Park, where I am advised by Prof. Hal Daumé III. I graduated from Columbia University with M.S. in Computer Science, and Sun Yat-Sen University with B.S. in Computational Mathematics.

I am broadly interested in human-AI collaboration and trustworthiness. My research focus on equipping large language/multimodal models with self-reasoning and self-improvement capabilities to be more useful to humans, including (i) pragmatic capability (ii) hallucination detection and correction.


  • [Feb 2024] New paper on Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Alternatives. Project Website
  • [Oct 2023] New paper on Hallucination Detection for Grounded Instruction Generation, accepted by Findings of EMNLP 2023. Project Website
  • [May 2023] New paper on Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models. Accepted by Finding of ACL 2023, and ICML ToM Workshop 2023 (received Outstanding Paper Award). Code and dataset released on Project Website