Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Percy Liang

Can Small and Synthetic Benchmarks Drive Modeling Innovation? A Retrospective Study of Question Answering Modeling Approaches


Feb 01, 2021
Nelson F. Liu, Tony Lee, Robin Jia, Percy Liang

* 40 pages, 13 figures; preprint 

  Access Paper or Ask Questions

Prefix-Tuning: Optimizing Continuous Prompts for Generation


Jan 01, 2021
Xiang Lisa Li, Percy Liang


  Access Paper or Ask Questions

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


Dec 16, 2020
Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang


  Access Paper or Ask Questions

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


Dec 14, 2020
Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang


  Access Paper or Ask Questions

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


Dec 13, 2020
Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, Yu Su


  Access Paper or Ask Questions

Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately


Dec 07, 2020
Fereshte Khani, Percy Liang


  Access Paper or Ask Questions

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


Nov 03, 2020
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli


  Access Paper or Ask Questions

Selective Classification Can Magnify Disparities Across Groups


Oct 27, 2020
Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang


  Access Paper or Ask Questions

RNNs can generate bounded hierarchical languages with optimal memory


Oct 15, 2020
John Hewitt, Michael Hahn, Surya Ganguli, Percy Liang, Christopher D. Manning

* EMNLP2020 + appendix typo fixes 

  Access Paper or Ask Questions

The EOS Decision and Length Extrapolation


Oct 14, 2020
Benjamin Newman, John Hewitt, Percy Liang, Christopher D. Manning

* 16 page, 7 Figures, 9 Tables, Blackbox NLP Workshop at EMNLP 2020 

  Access Paper or Ask Questions

Learning Adaptive Language Interfaces through Decomposition


Oct 11, 2020
Siddharth Karamcheti, Dorsa Sadigh, Percy Liang

* Accepted at the 1st Workshop for Interactive and Executable Semantic Parsing (IntEx-SemPar) @ EMNLP 2020. 11 pages, 5 figures 

  Access Paper or Ask Questions

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks


Oct 10, 2020
Stephen Mussmann, Robin Jia, Percy Liang

* In Findings of EMNLP 2020 

  Access Paper or Ask Questions

Task-Oriented Dialogue as Dataflow Synthesis


Oct 02, 2020
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

* TACL 2020 

  Access Paper or Ask Questions

Robustness to Spurious Correlations via Human Annotations


Aug 13, 2020
Megha Srivastava, Tatsunori Hashimoto, Percy Liang

* ICML 2020 final version, 16 pages, 9 figures 

  Access Paper or Ask Questions

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning


Aug 06, 2020
Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn

* Project web page at https://ezliu.github.io/dream 

  Access Paper or Ask Questions

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer


Jul 12, 2020
Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang


  Access Paper or Ask Questions

Concept Bottleneck Models


Jul 09, 2020
Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang

* ICML 2020 

  Access Paper or Ask Questions

Simplifying Models with Unlabeled Output Data


Jun 29, 2020
Sang Michael Xie, Tengyu Ma, Percy Liang


  Access Paper or Ask Questions

Selective Question Answering under Domain Shift


Jun 16, 2020
Amita Kamath, Robin Jia, Percy Liang

* ACL 2020 

  Access Paper or Ask Questions

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback


May 20, 2020
Michihiro Yasunaga, Percy Liang


  Access Paper or Ask Questions

Enabling Language Models to Fill in the Blanks


May 11, 2020
Chris Donahue, Mina Lee, Percy Liang

* To appear in the proceedings of ACL 2020 

  Access Paper or Ask Questions

An Investigation of Why Overparameterization Exacerbates Spurious Correlations


May 09, 2020
Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, Percy Liang


  Access Paper or Ask Questions

ExpBERT: Representation Engineering with Natural Language Explanations


May 05, 2020
Shikhar Murty, Pang Wei Koh, Percy Liang

* ACL 2020 

  Access Paper or Ask Questions

Robust Encodings: A Framework for Combating Adversarial Typos


May 04, 2020
Erik Jones, Robin Jia, Aditi Raghunathan, Percy Liang

* ACL 2020 

  Access Paper or Ask Questions