flâneur — a map of the web's best reading

SFT, RL, and On-Policy Distillation Through a Distributional Lens | wh

nrehiew.github.io · 3,658 words · saved by 4 readers

I have been thinking about post-training methods in terms of distributions. A language model is a distribution over sequences. When we post-train it and attempt to teach it a task, we are reshaping this distribution. Different post-training methods differ in how they reshape this distribution, what they treat as the target and how directly they define this target.

I have been thinking about post-training methods in terms of distributions. A language model is a distribution over sequences. When we post-train it and attempt to teach it a task, we are reshaping this distribution. Different post-training methods differ in how they reshape this distribution, what they treat as the target and how directly they define this target. This is neither a very precise statement nor is it meant to be fully rigorous. I just find it to be a useful mental model, but I think it explains a lot of the qualitative differences between SFT, RL, and On-Policy Distillation. This

Explore this link on the map →

saved by

related reading