Reposted by Abhishek Gupta
UW News put out a Q&A about our recent work on Variational Preference Learning, a technique for personalizing Reinforcement Learning from Human Feedback (RLHF) washington.edu/news/2024/12...
washington.edu
Q&A: New AI training method lets systems better adjust to users’ values
University of Washington researchers created a method for training AI systems — both for large language models like ChatGPT and for robots — that can better reflect users’ diverse values. It...
