Recent

• Provably Learning from Language Feedback
  Wanqiao Xu, Allen Nie, Ruijie Zheng, Aditya Modi, Adith Swaminathan, Ching-An Cheng (2025). arXiv preprint (2025).
  ArXiv PDF Best Paper @ ICML 2025 EXAIT
• Predicting Long Term Sequential Policy Value Using Softer Surrogates
  HyunJi Nam, Allen Nie, Ge Gao, Vasilis Syrgkanis, Emma Brunskill (2025). arXiv preprint (2025).
  ArXiv PDF
• EVOLvE: Evaluating and Optimizing LLMs For Exploration
  Allen Nie*, Yi Su*, Bo Chang*, Jonathan N Lee, Ed H Chi, Quoc V Le, Minmin Chen (2024). Work done at Google DeepMind. arXiv preprint (2024). ICML 2025.
  ICML 2025 PDF Oral @ BayLearn 2024
• Improving Parallel Program Performance with LLM Optimizers via Agent-System Interface
  Anjiang Wei*, Allen Nie*, Thiago SFX Teixeira, Rohan Yadav, Wonchan Lee, Ke Wang, and Alex Aiken (2024). Work done with Nvidia, Intel, Visa Research. arXiv preprint (2024). ICML 2025.
  ICML 2025 PDF Oral @ ICML 2025 PRAL
• OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
  Allen Nie, Yash Chandak, Christina J Yuan, Anirudhan Badrinath, Yannis Flet-Berliac, Emma Brunskil (2024). NeurIPS 2024. ArXiv.
  NeurIPS 2024 PDF

Reinforcement Learning

• Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets
  Anirudhan Badrinath, Yannis Flet-Berliac, Allen Nie, Emma Brunskill (2023). Presented at NeurIPS 2023.
  NeurIPS 2023 PDF
• Model-based Offline Reinforcement Learning with Local Misspecification
  Kefan Dong*, Allen Nie*, Yannis Flet-Berliac*, Emma Brunskill (2022). Oral at AAAI 2023. (Co-first authors, alphabetical order).
  AAAI 2023 PDF Oral @ AAAI 2023
• Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data
  Allen Nie, Yannis Flet-Berliac, Deon R. Jordan, William Steenbergen, Emma Brunskill (2022). Presented at NeurIPS 2022. Oral at AAAI 2023 Workshop on Reinforcement Learning Ready for Production.
  NeurIPS 2022 PDF Tweet Slides
• Giving Feedback on Interactive Student Programs with Meta-Exploration
  Evan Zheran Liu, Moritz Stephan, Allen Nie, Chris Piech, Emma Brunskill, Chelsea Finn (2022). Oral at NeurIPS 2022.
  NeurIPS 2022 PDF Oral @ NeurIPS 2022
• Play to Grade: Testing Coding Games as Classifying Markov Decision Process
  Allen Nie, Emma Brunskill, Chris Piech (2021). Presented at NeurIPS 2021.
  NeurIPS 2021 PDF Blog

Foundation Model for Decision Making

• Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
  Ching-An Cheng*, Allen Nie*, Adith Swaminathan* (2024). (Equal contribution). NeurIPS 2024. arXiv preprint arXiv:2406.16218 (2024).
  NeurIPS 2024 PDF
• The Importance of Directional Feedback for LLM-based Optimizers
  Allen Nie, Ching-An Cheng, Andrey Kolobov, Adith Swaminathan (2023). Presented at NeurIPS 2023 Foundation Model for Decision Making Workshop.
  NeurIPS 2023 Workshop PDF
• MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
  Allen Nie, Yuhui Zhang, Atharva Amdekar, Chris Piech, Tatsunori Hashimoto, Tobias Gerstenberg (2023). Presented at NeurIPS 2023.
  NeurIPS 2023 PDF Included in BIG-Bench Hard Oral @ NeurIPS 2023 MP2
• LLF-Bench: Benchmark for Interactive Learning from Language Feedback
  Ching-An Cheng*, Andrey Kolobov*, Dipendra Misra*, Allen Nie*, Adith Swaminathan* (2024). (Equal contribution, alphabetical order). ArXiv release. Submitted for NeurIPS 2024 Benchmark Track.
  ArXiv PDF

Reinforcement Learning For Education

• The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters’ Exam Performances
  Allen Nie, Yash Chandak, Miroslav Suzara, Ali Malik, Juliette Woodrow, Matt Peng, Mehran Sahami, Emma Brunskill, Chris Piech. Center for Open Science (2024).
  L@S 2025 PDF Press (ACM XRDS Article)
• Reinforcement Learning Tutor Better Supported Lower Performers in a Math Task
  Sherry Ruan*, Allen Nie*, William Steenbergen, Jiayu He, J. Q. Zhang, Meng Guo, Yao Liu, ..., James A Landay, Emma Brunskill. arXiv preprint arXiv:2304.04933 (2023).
  Machine Learning Journal 2023 PDF
• Estimating the Causal Treatment Effect of Unproductive Persistence
  Amelia Leon, Allen Nie, Yash Chandak, Emma Brunskill (2024). Proceedings of the 14th Learning Analytics and Knowledge (LAK) Conference. Kyoto, Japan. (Nominated for Best Short Paper Award).
  LAK 2024 PDF
• Understanding the Impact of Reinforcement Learning Personalization on Subgroups of Students in Math Tutoring
  Allen Nie*, Ann-Katrin Reuel*, and Emma Brunskill. Presented at AIED 2023. The 24th International Conference on Artificial Intelligence in Education. Tokyo, Japan.
  AIED 2023 PDF

Natural Language Processing and Understanding

• Pragmatic Issue-Sensitive Image Captioning
  Allen Nie, Reuben Cohn-Gordon, and Chris Potts. (2020). Presented at EMNLP 2020. Oral at CoNLL 2020.
  EMNLP 2020 PDF Blog Oral @ CoNLL 2020
• Learning to Explain: Answering Why-Questions via Rephrasing.
  Allen Nie, Erin D. Bennett, and Noah D. Goodman (2019). Proceedings of the 1st Workshop NLP for Conversational AI. Florence, Italy. ACL 2019.
  ACL 2019 Workshop PDF Code Demo
• DisSent: Sentence Representation Learning from Explicit Discourse Relations
  Allen Nie, Erin D. Bennett, Noah D. Goodman (2017). Published in ACL 2019. Florence Italy.
  ACL 2019 PDF Code ACL
• Data Noising as Smoothing in Neural Network Sequence Models Ziang, X., Sida W., Jiwei L., Levy, D., Nie A., Jurafsky, Dan & Ng, Andrew, (2016). 5th International Conference on Learning Representations (ICLR). Toulon, France. (Oral at BayLearn 2016)
  ICLR 2016 PDF Oral @ BayLearn 2016 (<5%)

Collaborations and Applications

• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
  Aarohi Srivastava, ..., Allen Nie, ..., Tatsu Hashimoto, Tobias Gerstenberg, ... (2022). ArXiv. Presented at NeurIPS 2022 (Lead by Google Research, Jascha Sohl-Dickstein team).
  TMLR 2023 PDF
• On the Opportunities and Risks of Foundation Models
  Rishi Bommasani, Drew A. Hudson, ..., Allen Nie, ..., Percy Liang. (2021). ArXiv. Presented at Center for Research on Foundation Models (CRFM).
  PDF
• LitGen: Genetic Literature Recommendation Guided by Human Explanations
  Allen Nie, Arturo L. Pineda, Matt W. Wright, Hannah Wand, Bryan Wulf, Helio A. Costa, Ronak Y. Patel, Carlos D. Bustamante, and James Zou. Pacific Symposium of Biocomputing (2020): Artificial Intelligence for Enhancing Clinical Medicine Session.
  PSB 2020 PDF Code
• VetTag: improving automated veterinary diagnosis coding via large-scale language modeling.
  Yuhui Zhang*, Allen Nie*, Ashley Zehnder, James Zou (2019). Nature (npj) Digital Medicine 2, Article: 35.
  npj Digital Medicine 2019 PDF Demo
• DeepTag: inferring diagnoses from veterinary clinical notes.
  Allen Nie, Ashley Zehnder, Rodney L. Page, Arturo L. Pineda, Manuel A. Rivas, Carlos D. Bustamante, James Zou., (2018). Nature (npj) Digital Medicine 1, Article: 60.
  npj Digital Medicine 2018 PDF Code Demo

Cognitive Science and Psycholinguistics

• Representations of Time Affect Willingness to Wait for Future Rewards
  Thorstad, R., Nie, A., & Wolff, P. (2015). 37th Annual Conference of the Cognitive Science Society. Pasadena, California.
  CogSci 2015 PDF
• Computational Exploration to Linguistic Structures of Future, Classification and Categorization
  Nie, A., Sheppard, J., Choi, J., Copley, B., Wolff, P., (2015). The North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Denver, Colorado.
  ACL 2015 Workshop PDF