Ken Liu — accepted AI-conference papers

2025

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

Yangsibo Huang, Milad Nasr, Anastasios Nikolas Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo +7

ICML 2025oral

It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to sele…

Cited by 4 Source ↗PDF ↗Scholar ↗

2025

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Ken Liu, Christopher A. Choquette-Choo, Matthew Jagielski, Peter Kairouz, Sanmi Koyejo, Percy Liang +1

ICML 2025spotlight

An important question today is whether a given text was used to train a large language model (LLM). A completion test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member b…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Kevin Klyman, Matthew Jagielski, Katja Filippova +31

NeurIPS 2025oral

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific infor…

Cited by 0 Source ↗Scholar ↗

2023

Differentially Private Adaptive Optimization with Delayed Preconditioners

Tian Li, Manzil Zaheer, Ken Liu, Sashank J. Reddi, Hugh Brendan McMahan, Virginia Smith

ICLR 2023poster

Privacy costs may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive optimization. In this work, we explore techniques to estimat…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2022

On Privacy and Personalization in Cross-Silo Federated Learning

Ken Liu, Shengyuan Hu, Steven Wu, Virginia Smith

NeurIPS 2022accept

While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cross-silo FL, a setting characterized by a limited number of clients each containing many data subjects. In cross-silo FL…

Cited by 72 Source ↗PDF ↗code ↗Scholar ↗