Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas Paper • 2412.14843 • Published Dec 19, 2024
SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks Paper • 2412.16783 • Published Dec 21, 2024
Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective Paper • 2410.16586 • Published Oct 22, 2024