Percy Liang

Extending the WILDS Benchmark for Unsupervised Adaptation

Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

LinkBERT: Pretraining Language Models with Document Links

Michihiro Yasunaga, Jure Leskovec, Percy Liang

Comments Published at ACL 2022. Code, data, and pretrained models are available at https://github.com/michiyasunaga/LinkBERT

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang

Comments ICLR (Oral) 2022

CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities

Mina Lee, Percy Liang, Qian Yang

Comments Published as a conference paper at CHI 2022

GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

Xikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren, Percy Liang, Christopher D. Manning, Jure Leskovec

Comments Published at ICLR 2022. All code, data, and pretrained models are available at https://github.com/snap-stanford/GreaseLM

Unlabeled Data Improves Adversarial Robustness

Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, Percy Liang, John C. Duchi

Comments Corrected some math typos in the proof of Lemma 1

Stronger Data Poisoning Attacks Break Data Sanitization Defenses

Pang Wei Koh, Jacob Steinhardt, Percy Liang

Comments This paper was first published on arXiv in 2018 and has since been edited for clarity

Journal ref Machine Learning, 2021

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn

Comments International Conference on Machine Learning (ICML), 2021

LILA: Language-Informed Latent Actions

Siddharth Karamcheti, Megha Srivastava, Percy Liang, Dorsa Sadigh

Comments Accepted at the 5th Conference on Robot Learning (CoRL). Joint first authorship. 21 Pages, 11 Figures

LM-Critic: Language Models for Unsupervised Grammatical Error Correction

Michihiro Yasunaga, Jure Leskovec, Percy Liang

Comments EMNLP 2021. Code & data available at https://github.com/michiyasunaga/LM-Critic

Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

John Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt

Just Train Twice: Improving Group Robustness without Training Group Information

Evan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan, Pang Wei Koh, Shiori Sagawa, Percy Liang, Chelsea Finn

Comments International Conference on Machine Learning (ICML), 2021

Conditional probing: measuring usable information beyond a baseline

John Hewitt, Kawin Ethayarajh, Percy Liang, Christopher D. Manning

Comments EMNLP 2021 + typo fixes

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

Fahim Tajwar, Ananya Kumar, Sang Michael Xie, Percy Liang

Comments ICML Workshop on Uncertainty & Robustness in Deep Learning, 2021

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton A. Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang

Codified audio language modeling learns useful representations for music information retrieval

Rodrigo Castellon, Chris Donahue, Percy Liang

Comments To appear in the proceedings of ISMIR 2021

Break-It-Fix-It: Unsupervised Learning for Program Repair

Michihiro Yasunaga, Percy Liang

Comments ICML 2021. Code & data available at https://github.com/michiyasunaga/bifi

Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality

Mina Lee, Chris Donahue, Robin Jia, Alexander Iyabor, Percy Liang

Comments Published as a conference paper at NAACL 2021

Selective Classification Can Magnify Disparities Across Groups

Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang

Comments Published at the International Conference on Learning Representations (ICLR) 2021

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang

Comments ICLR 2021

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, Yu Su

Comments Accepted to TheWebConf 2021 (previously WWW)

Task-Oriented Dialogue as Dataflow Synthesis

Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov

Journal ref Transactions of the Association for Computational Linguistics 2020 Vol. 8, 556-571

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Xiang Lisa Li, Percy Liang

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

Comments Edited for clarity from the ICML 2020 version

Understanding Black-box Predictions via Influence Functions

Pang Wei Koh, Percy Liang

Comments International Conference on Machine Learning, 2017. (This version adds more historical references and fixes typos.)

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

Fereshte Khani, Percy Liang

Feature Noise Induces Loss Discrepancy Across Groups

Fereshte Khani, Percy Liang

Comments ICML 2020

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli

Certified Defenses against Adversarial Examples

Aditi Raghunathan, Jacob Steinhardt, Percy Liang

Comments Published at the International Conference on Learning Representations (ICLR) 2018

Selection via Proxy: Efficient Data Selection for Deep Learning

Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia

Comments ICLR 2020