activity
20152023
most citedCoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities

337 citations · 3k across the 78 of their papers we have counts for

collaborators
Showing 2017Show all

5 papers · 1 filter

stat.ML2017★ 1 cited

Unsupervised Transformation Learning via Convex Relaxations

Tatsunori B. Hashimoto, John C. Duchi, Percy Liang

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised a…

cs.CL2017★ 5 cited

Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

Yuchen Zhang, Panupong Pasupat, Percy Liang

To learn a semantic parser from denotations, a learning algorithm must search over a combinatorially large space of logical forms for ones consistent with the annotated denotations…

cs.CL2017★ 263 cited

Adversarial Examples for Evaluating Reading Comprehension Systems

Robin Jia, Percy Liang

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To…

cs.SE2017★ 28 cited

Developing Bug-Free Machine Learning Systems With Formal Mathematics

Daniel Selsam, Percy Liang, David L. Dill

Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual im…

cs.LG2017★ 82 cited

Certified Defenses for Data Poisoning Attacks

Jacob Steinhardt, Pang Wei Koh, Percy Liang

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the…