2 citations · 3 across the 5 of their papers we have counts for
5 papers
Quantifying the Effect of Test Set Contamination on Generative Evaluations
Rylan Schaeffer, Joshua Kazdan, Baber Abbasi +8
As frontier AI systems are pretrained on web-scale data, test set contamination has become a critical concern for accurately assessing their capabilities. While research has thorou…
UQ: Assessing Language Models on Unsolved Questions
Fan Nie, Ken Ziyu Liu, Zihao Wang +11
Benchmarks shape progress in AI research. A useful benchmark should be both difficult and realistic: questions should challenge frontier models while also reflecting real-world usa…
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
Ken Ziyu Liu, Christopher A. Choquette-Choo, Matthew Jagielski +4
An important question today is whether a given text was used to train a large language model (LLM). A \emph{completion} test is often employed: check if the LLM completes a suffici…
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
Yangsibo Huang, Milad Nasr, Anastasios Angelopoulos +10
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 ski…
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen +34
"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, copyri…