protologue

Self-Refine

Also called iterative refinement, self-critique.

Self-Refine is an iterative method in which the same model generates an output, critiques it with specific feedback, and revises it, repeating until a stopping condition is met.

Description

It requires no extra training or separate models. Madaan et al. reported improvements across tasks such as code optimization, dialogue, and math reasoning, though later work found that unaided self-correction of reasoning can fail without external signals.

Sources

  1. Madaan et al. (2023). Self-Refine: Iterative Refinement with Self-Feedback.
  2. Huang et al. (2023). Large Language Models Cannot Self-Correct Reasoning Yet.

Cite this entry

Protologue. (2026). Self-Refine. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0047). https://protologue.com/t/self-refine/

BibTeX
@misc{protologue_self_refine,
  title = {Self-Refine},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
  note = {Entry PTL-0047},
  url = {https://protologue.com/t/self-refine/}
}

Markdown JSON