Published papers at ICML 2024: 'Linguistic Calibration of Language Models' and 'Language Models with Conformal Factuality Guarantees'.
Multiple publications at ICLR 2024, including 'Proving test set contamination in black box language models', 'Benchmarking and improving generator-validator consistency of language models', and 'Identifying the risks of lm agents with an lm-emulated sandbox'.
Published at NeurIPS 2023: 'AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback' and 'Likelihood-Based Diffusion Language Models'.
Published in TMLR 2024: 'Robust Distortion-free Watermarks for Language Models'.
Advising numerous postdocs and graduate students in collaboration with faculty such as Percy Liang, Tengyu Ma, Carlos Guestrin, Emmanuel Candes, and others.