Miao Xiong

I am a PhD student at National University of Singapore advised by Prof. Bryan Hooi . I obtained my undergraduate with double majors in Computer Science and Statistics at Zhejiang University.

My research interests lie in Trustworthy and Responsible AI, especially addressing trust-related challenges in foundation models. I am currently working on topics around LLMs (hallucination mitigation, RAG, constraint decoding etc). I also study Uncertainty Estimation, in the context of Calibration, Failure Prediction and Out-of-Distribution Detection to enhance the reliability of AI-based decision making system.

I am passionate about advancing AI towards greater safety, equity, and sustainability, and remain enthusiastic about embracing new challenges in this dynamic field.

Google Scholar  /  GitHub  /  Twitter  /  Linkdin  /  Email

News
  • 2024-04 Our paper "In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation" is accepted at ICML 2024!
  • 2024-01 Our paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs" is accepted at ICLR 2024!
  • 2023-09 Our paper "Proximity-Informed Calibration of Deep Neural Networks" is accepted at NeurIPS 2023 as a Spotlight!
Research