Percy Liang

is this you? claim profile

∙ 0 followers
Stanford University

Assistant Professor at Stanford University

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

We consider repair tasks: given a critic (e.g., compiler) that assesses ...
06/11/2021 ∙ by Michihiro Yasunaga, et al. ∙ 10 ∙ share

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

We release a new benchmark for lexical substitution, the task of finding...
06/08/2021 ∙ by Mina Lee, et al. ∙ 0 ∙ share

read it
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

The problem of answering questions using knowledge from pre-trained lang...
04/13/2021 ∙ by Michihiro Yasunaga, et al. ∙ 15 ∙ share

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

Datasets are not only resources for training accurate, deployable system...
02/01/2021 ∙ by Nelson F. Liu, et al. ∙ 0 ∙ share

read it
Prefix-Tuning: Optimizing Continuous Prompts for Generation

Fine-tuning is the de facto way to leverage large pretrained language mo...
01/01/2021 ∙ by Xiang Lisa Li, et al. ∙ 0 ∙ share

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

Distribution shifts can cause significant degradation in a broad range o...
12/14/2020 ∙ by Pang Wei Koh, et al. ∙ 11 ∙ share

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

Consider a prediction setting where a few inputs (e.g., satellite images...
12/08/2020 ∙ by Sang Michael Xie, et al. ∙ 8 ∙ share

read it
Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately

The presence of spurious features interferes with the goal of obtaining ...
12/07/2020 ∙ by Fereshte Khani, et al. ∙ 0 ∙ share

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

Existing studies on question answering on knowledge bases (KBQA) mainly ...
11/16/2020 ∙ by Yu Gu, et al. ∙ 0 ∙ share

read it
Selective Classification Can Magnify Disparities Across Groups

Selective classification, in which models are allowed to abstain on unce...
10/27/2020 ∙ by Erik Jones, et al. ∙ 0 ∙ share

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

Convex relaxations have emerged as a promising approach for verifying de...
10/22/2020 ∙ by Sumanth Dathathri, et al. ∙ 6 ∙ share

read it
RNNs can generate bounded hierarchical languages with optimal memory

Recurrent neural networks empirically generate natural language with hig...
10/15/2020 ∙ by John Hewitt, et al. ∙ 23 ∙ share

read it
The EOS Decision and Length Extrapolation

Extrapolation to unseen sequence lengths is a challenge for neural gener...
10/14/2020 ∙ by Benjamin Newman, et al. ∙ 0 ∙ share

read it
Learning Adaptive Language Interfaces through Decomposition

Our goal is to create an interactive natural language interface that eff...
10/11/2020 ∙ by Siddharth Karamcheti, et al. ∙ 0 ∙ share

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

Many pairwise classification tasks, such as paraphrase detection and ope...
10/10/2020 ∙ by Stephen Mussmann, et al. ∙ 0 ∙ share

read it
Task-Oriented Dialogue as Dataflow Synthesis

We describe an approach to task-oriented dialogue in which dialogue stat...
09/24/2020 ∙ by Jacob Andreas, et al. ∙ 0 ∙ share

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

We seek to efficiently learn by leveraging shared structure between diff...
08/06/2020 ∙ by Evan Zheran Liu, et al. ∙ 6 ∙ share

read it
Robustness to Spurious Correlations via Human Annotations

The reliability of machine learning systems critically assumes that the ...
07/13/2020 ∙ by Megha Srivastava, et al. ∙ 14 ∙ share

read it
Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Model-based reinforcement learning (RL) is appealing because (i) it enab...
07/12/2020 ∙ by Evan Zheran Liu, et al. ∙ 12 ∙ share

read it
Concept Bottleneck Models

We seek to learn models that we can interact with using high-level conce...
07/09/2020 ∙ by Pang Wei Koh, et al. ∙ 14 ∙ share

read it
Simplifying Models with Unlabeled Output Data

We focus on prediction problems with high-dimensional outputs that are s...
06/29/2020 ∙ by Sang Michael Xie, et al. ∙ 8 ∙ share

read it
Selective Question Answering under Domain Shift

To avoid giving wrong answers, question answering (QA) models need to kn...
06/16/2020 ∙ by Amita Kamath, et al. ∙ 0 ∙ share

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

We consider the problem of learning to repair programs from diagnostic f...
05/20/2020 ∙ by Michihiro Yasunaga, et al. ∙ 0 ∙ share

read it
Enabling Language Models to Fill in the Blanks

We present a simple approach for text infilling, the task of predicting ...
05/11/2020 ∙ by Chris Donahue, et al. ∙ 0 ∙ share

read it
An Investigation of Why Overparameterization Exacerbates Spurious Correlations

We study why overparameterization – increasing model size well beyond th...
05/09/2020 ∙ by Shiori Sagawa, et al. ∙ 0 ∙ share

read it
ExpBERT: Representation Engineering with Natural Language Explanations

Suppose we want to specify the inductive bias that married couples typic...
05/05/2020 ∙ by Shikhar Murty, et al. ∙ 13 ∙ share

read it
Robust Encodings: A Framework for Combating Adversarial Typos

Despite excellent performance on many tasks, NLP systems are easily fool...
05/04/2020 ∙ by Erik Jones, et al. ∙ 0 ∙ share

read it
Understanding Self-Training for Gradual Domain Adaptation

Machine learning systems must adapt to data distributions that evolve ov...
02/26/2020 ∙ by Ananya Kumar, et al. ∙ 5 ∙ share

read it
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

Adversarial training augments the training set with perturbations to imp...
02/25/2020 ∙ by Aditi Raghunathan, et al. ∙ 42 ∙ share

read it
Noise Induces Loss Discrepancy Across Groups for Linear Regression

We study the effect of feature noise (measurement error) on the discrepa...
11/22/2019 ∙ by Fereshte Khani, et al. ∙ 0 ∙ share

read it
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Overparameterized neural networks can be highly accurate on average on a...
11/20/2019 ∙ by Shiori Sagawa, et al. ∙ 0 ∙ share

read it
Learning Autocomplete Systems as a Communication Game

We study textual autocomplete—the task of predicting a full sentence fro...
11/16/2019 ∙ by Mina Lee, et al. ∙ 0 ∙ share

read it
Shaping Visual Representations with Language for Few-shot Classification

Language is designed to convey useful information about the world, thus ...
11/06/2019 ∙ by Jesse Mu, et al. ∙ 0 ∙ share

read it
Verified Uncertainty Calibration

Applications such as weather forecasting and personalized medicine deman...
09/23/2019 ∙ by Ananya Kumar, et al. ∙ 2 ∙ share

read it
Designing and Interpreting Probes with Control Tasks

Probes, supervised models trained to predict properties (like parts-of-s...
09/08/2019 ∙ by John Hewitt, et al. ∙ 0 ∙ share

read it
Distributionally Robust Language Modeling

Language models are generally trained on data spanning a wide range of t...
09/04/2019 ∙ by Yonatan Oren, et al. ∙ 0 ∙ share

read it
Certified Robustness to Adversarial Word Substitutions

State-of-the-art NLP models can often be fooled by adversaries that appl...
09/03/2019 ∙ by Robin Jia, et al. ∙ 0 ∙ share

read it
A Tight Analysis of Greedy Yields Subexponential Time Approximation for Uniform Decision Tree

Decision Tree is a classic formulation of active learning: given n hypot...
06/26/2019 ∙ by Ray Li, et al. ∙ 0 ∙ share

read it
Selection Via Proxy: Efficient Data Selection For Deep Learning

Data selection methods such as active learning and core-set selection ar...
06/26/2019 ∙ by Cody Coleman, et al. ∙ 12 ∙ share

read it
Adversarial Training Can Hurt Generalization

While adversarial training can improve robust accuracy (against an adver...
06/14/2019 ∙ by Aditi Raghunathan, et al. ∙ 0 ∙ share

read it
SPoC: Search-based Pseudocode to Code

We consider the task of mapping pseudocode to long programs that are fun...
06/12/2019 ∙ by Sumith Kulal, et al. ∙ 0 ∙ share

read it
Maximum Weighted Loss Discrepancy

Though machine learning algorithms excel at minimizing the average loss ...
06/08/2019 ∙ by Fereshte Khani, et al. ∙ 0 ∙ share

read it
Unlabeled Data Improves Adversarial Robustness

We demonstrate, theoretically and empirically, that adversarial robustne...
05/31/2019 ∙ by Yair Carmon, et al. ∙ 0 ∙ share

read it
On the Accuracy of Influence Functions for Measuring Group Effects

Influence functions estimate the effect of removing particular training ...
05/30/2019 ∙ by Pang Wei Koh, et al. ∙ 0 ∙ share

read it
Pre-training Graph Neural Networks

Many applications of machine learning in science and medicine, including...
05/29/2019 ∙ by Weihua Hu, et al. ∙ 24 ∙ share

read it
Pun Generation with Surprise

We tackle the problem of generating a pun sentence given a pair of homop...
04/15/2019 ∙ by He He, et al. ∙ 0 ∙ share

read it
Unifying Human and Statistical Evaluation for Natural Language Generation

How can we measure whether a natural language generation system produces...
04/04/2019 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Defending against Whitebox Adversarial Attacks via Randomized Discretization

Adversarial perturbations dramatically decrease the accuracy of state-of...
03/25/2019 ∙ by Yuchen Zhang, et al. ∙ 0 ∙ share

read it
Ambitious Data Science Can Be Painless

Modern data science research can involve massive computational experimen...
01/25/2019 ∙ by Hatef Monajemi, et al. ∙ 0 ∙ share

read it
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss

Uncertainty sampling, a popular active learning algorithm, is used to re...
12/05/2018 ∙ by Stephen Mussmann, et al. ∙ 0 ∙ share

read it

Percy Liang

Featured Co-authors