In Self-Refine, a single frozen LLM acts as generator, critic, and rewriter in a prompt-only loop, and the paper reports...

In Self-Refine, a single frozen LLM acts as generator, critic, and rewriter in a prompt-only loop, and the paper reports about 20 points of average lift across seven tasks without any training, RL, or external signal. The gains vary widely by task: small on math reasoning, but large on dialogue and constrained generation, where what counts as "good" is hardest to define from a one-line critique.https://benjaminhan.net/posts/20260516-self-refine/?utm_source=mastodon&utm_medium=social#SelfRefine #LLMs #AI #Reasoning #Metacognition