ProRefine: Inference-time Prompt Refinement with Textual Feedback
Published in arXiv preprint arXiv:2506.05305, 2025
Effective prompt engineering is crucial for eliciting desired behaviors from large language models. This paper introduces ProRefine, a method for refining prompts at inference time using textual feedback. Our approach iteratively improves prompts based on the model’s outputs and explicit feedback signals, enabling better task performance without modifying the underlying model weights.
Recommended citation: @article{pandita2025prorefine, title={ProRefine: Inference-time Prompt Refinement with Textual Feedback}, author={Pandita, Deepak and Weerasooriya, Tharindu Cyril and Shah, Ankit Parag and Homan, Christopher M and Wei, Wei}, journal={arXiv preprint arXiv:2506.05305}, year={2025} }
Download Paper