About Me

I am a Ph.D. candidate majoring in Social & Engineering Systems and Statistics at MIT IDSS and LIDS. I have been fortunately working with Prof. Marzyeh Ghassemi on machine learning for healthcare.

My current research centers around two primary questions:

• How can we reliably distinguish when language models should incorporate human inputs for effective knowledge updates and when they should resist malicious instructions, improving the alignment and ethics of these tools in real-world applications?
• How can we leverage uncertainty quantification, mechanistic interpretations, and reasoning capabilities of language models to effectively assess, understand, and align their behaviors for trustworthy deployment, especially in high-stakes scenarios?

For more information about my background and qualifications, please refer to my CV.