Apply for a research position at Microsoft Research New York & collaborate with academia to advance economics research, prediction markets & ML.

View 3 comments: Delete the space?

Learning from human preference data has emerged as the dominant paradigm for fine-tuning large language models (LLMs). The two most common families of techniques -- online reinforcement learning (RL) ...

Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs, filters or reweights...