Researcher, Cohere
2 papers at NeurIPS 2025
Chatbot Arena has become a leading platform for ranking AI models. Our extensive study uncovers hidden dynamics that distort rankings and provides concrete steps to enhance fairness and transparency in evaluation of models on Chatbot Arena.
An optimization approach that bridges the gap between training and inference techniques via a highly detailed taxonomy of data characteristics to explicitly control generation attributes and implicitly condition generations during inference.
