19 citations · 37 across the 14 of their papers we have counts for
16 papers
Personalized Recommendations Without Inducing Congestion: Mitigating Disparities in the NYC High School Match
Erica Chiang, Kenny Peng, Rebecca Lichtenstein +7
Algorithmic recommendations can help participants navigate large matching markets. For example, recommendations for school and college choices may reduce information frictions and…
A Testable Theory of Atomic Features
Kenny Peng, Jon Kleinberg, Nikhil Garg
We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a model, sparse dictionaries (e.g.…
How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
Nikhil Garg, Jon Kleinberg, Kenny Peng
We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate…
Correlated Errors in Large Language Models
Elliot Kim, Avi Garg, Kenny Peng +1
Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfull…
Position: Use Sparse Autoencoders to Discover Unknowns
Kenny Peng, Rajiv Movva, Jon Kleinberg +2
While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptua…
Sparse Autoencoders for Hypothesis Generation
Rajiv Movva, Kenny Peng, Nikhil Garg +2
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three…
A No Free Lunch Theorem for Human-AI Collaboration
Kenny Peng, Nikhil Garg, Jon Kleinberg
The gold standard in human-AI collaboration is complementarity -- when combined performance exceeds both the human and algorithm alone. We investigate this challenge in binary clas…
Stable Tables
Kenny Peng
We consider equilibrium one-on-one conversations between neighbors on a circular table, with the goal of assessing the likelihood of a (perhaps) familiar situation: sitting at a ta…
Rescuing Counterspeech: A Bridging-Based Approach to Combating Misinformation
Kenny Peng, James Grimmelmann
Social media has a misinformation problem, and counterspeech -- fighting bad speech with more speech -- has been an ineffective solution. Here, we argue that bridging-based ranking…
Wisdom and Foolishness of Noisy Matching Markets
Kenny Peng, Nikhil Garg
We consider a many-to-one matching market where colleges share true preferences over students but make decisions using only independent noisy rankings. Each student has a true valu…
Monoculture in Matching Markets
Kenny Peng, Nikhil Garg
Algorithmic monoculture arises when many decision-makers rely on the same algorithm to evaluate applicants. An emerging body of work investigates possible harms of this kind of hom…
REFORMS: Reporting Standards for Machine Learning Based Science
Sayash Kapoor, Emily Cantrell, Kenny Peng +16
Machine learning (ML) methods are proliferating in scientific research. However, the adoption of these methods has been accompanied by failures of validity, reproducibility, and ge…
Reconciling the accuracy-diversity trade-off in recommendations
Kenny Peng, Manish Raghavan, Emma Pierson +2
In recommendation settings, there is an apparent trade-off between the goals of accuracy (to recommend items a user is most likely to want) and diversity (to recommend items repres…
Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers
Rajiv Movva, Sidhika Balachandar, Kenny Peng +3
Large language models (LLMs) are dramatically influencing AI research, spurring discussions on what has changed so far and how to shape the field's future. To clarify such question…
Mixing times of one-sided -transposition shuffles
Evita Nestoridi, Kenny Peng, Bryan Wong
We study mixing times of the one-sided -transposition shuffle. We prove that this shuffle mixes relatively slowly, even for big. Using the recent ``lifting eigenvectors'' te…
Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers
Kenny Peng, Arunesh Mathur, Arvind Narayanan
Machine learning datasets have elicited concerns about privacy, bias, and unethical applications, leading to the retraction of prominent datasets such as DukeMTMC, MS-Celeb-1M, and…