@misc{xu2023reprompting,
author = {Xu, Weijia and Banburski-Fahey, Andrzej and Jojic, Nebojsa},
title = {Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling},
howpublished = {arXiv},
year = {2023},
month = {May},
abstract = {We introduce Reprompting, an iterative sampling algorithm that searches for the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, we infer CoT recipes that work consistently well for a set of training samples. Our method iteratively samples new recipes using previously sampled solutions as parent prompts to solve other training problems. On five Big-Bench Hard tasks that require multi-step reasoning, Reprompting achieves consistently better performance than the zero-shot, few-shot, and human-written CoT baselines. Reprompting can also facilitate transfer of knowledge from a stronger model to a weaker model leading to substantially improved performance of the weaker model. Overall, Reprompting brings up to +17 point improvements over the previous state-of-the-art method that uses human-written CoT prompts.},
url = {http://approjects.co.za/?big=en-us/research/publication/reprompting-automated-chain-of-thought-prompt-inference-through-gibbs-sampling/},
}