Research
A complete list of publications can be found on Google Scholar. Here are some recent papers that I'm proud of:
-
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
-
CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion
-
MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
-
Don't lie to your friends: Learning what you know from collaborative self-play
-
Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking
-
MD3: The multi-dialect dataset of dialogues
-
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
-
Underspecification presents challenges for credibility in modern machine learning
Professional Service
- Workshop co-organizer: Evaluation of Interactive Agents (NeurIPS 2026); Distribution Shifts (NeurIPS 2023 and 2022); NLP and Computational Social Science (EMNLP 2016); Language Technologies and Computational Social Science (ACL 2014).
- Journals: editorial boards of TACL (current), Computational Linguistics (past); reviewer for PNAS, Science, Communications of the ACM, Transactions on Machine Learning Research, Journal of Machine Learning Research, Journal of Sociolinguistics, Language in Society, etc.
- (Senior) Area Chair, Program Committee, and other roles: ACL, CoLM, EMNLP, ICLR, ICML, NAACL, NeurIPS, etc.
Georgia Tech (2012–2019)
From 2012–2019 I was on the faculty at Georgia Tech, where most of my teaching effort was dedicated to designing and delivering two courses: Natural Language Processing and Computational Social Science.
PhD Advisees