home.social

#selfrefine — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #selfrefine, aggregated by home.social.

  1. 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.

    benjaminhan.net/posts/20260516

    #SelfRefine #LLMs #AI #Reasoning #Metacognition