P
Percy Liang
Researcher at Stanford University
Publications - 369
Citations - 42254
Percy Liang is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Parsing. The author has an hindex of 75, co-authored 306 publications receiving 29242 citations. Previous affiliations of Percy Liang include University of California, Berkeley & Google.
Papers
More filters
Proceedings Article
Tensor Factorization via Matrix Factorization
TL;DR: A new method is proposed for CP tensor factorization that uses random projections to reduce the problem to simultaneous matrix diagonalization, and it is proved that a small number random projections essentially preserves the spectral information in the tensor.
Journal ArticleDOI
Whose Opinions Do Language Models Reflect?
TL;DR: This paper found substantial misalignment between the views reflected by current LMs and those of US demographic groups, on par with the Democrat-Republican divide on climate change, even after explicitly steering the LMs towards particular demographic groups.
Proceedings ArticleDOI
Efficient geometric algorithms for parsing in two dimensions
TL;DR: This paper introduces (and unify) several types of geometrical data structures which can be used to significantly accelerate parsing time, and introduces a clean design for the parsing software, and test the same parsing framework with various geometric constraints to determine the most effective combination.
Proceedings ArticleDOI
A dynamic evaluation of the precision of static heap abstractions
TL;DR: The goal of this paper is to investigate how various refinements of allocation sites can improve precision, in particular, abstractions that use call stack, object recency, and heap connectivity information.
Proceedings ArticleDOI
Social Simulacra: Creating Populated Prototypes for Social Computing Systems
Joon Sung Park,Lindsay Popowski,Carrie J. Cai,Meredith Ringel Morris,Percy Liang,Michael S. Bernstein +5 more
TL;DR: It is demonstrated that social simulacra shift the behaviors that they generate appropriately in response to design changes, and that they enable exploration of “what if?” scenarios where community members or moderators intervene.