Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
Abstract
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recipes that work consistently well for a set of training samples by iteratively sampling new recipes using previously sampled recipes as parent prompts to solve other training problems. We conduct extensive experiments on 20 challenging reasoning tasks. Results show that Reprompting outperforms human-written CoT prompts substantially by +9.4 points on average. It also achieves consistently better performance than the state-of-the-art prompt optimization and decoding algorithms.
Cite
Text
Xu et al. "Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling." International Conference on Machine Learning, 2024.Markdown
[Xu et al. "Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/xu2024icml-reprompting/)BibTeX
@inproceedings{xu2024icml-reprompting,
title = {{Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling}},
author = {Xu, Weijia and Banburski, Andrzej and Jojic, Nebojsa},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {54852-54865},
volume = {235},
url = {https://mlanthology.org/icml/2024/xu2024icml-reprompting/}
}