Samuel Dooley

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Multi-objective Differentiable Neural Architecture Search

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking

LLMs Boost the Performance of Decision Trees on Tabular Data across Sample Sizes

To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination

Large Language Models Must Be Taught to Know What They Don’t Know