Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt engineering methods require significant amounts of labeled data, access to model parameters, or both. We introduce a new method for selecting prompt templates \textit{without labeled examples} and \textit{without direct access to the model}. Specifically, over a set of candidate templates, we choose the template that maximizes the mutual information between the input and the corresponding model output. Across 8 datasets representing 7 distinct NLP tasks, we show that when a template has high mutual information, it also has high accuracy on the task. On the largest model, selecting prompts with our method gets 90\% of the way from the average prompt accuracy to the best prompt accuracy and requires no ground truth labels.
@article{arxiv.2203.11364,
title = {An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels},
author = {Taylor Sorensen and Joshua Robinson and Christopher Michael Rytting and Alexander Glenn Shaw and Kyle Jeffrey Rogers and Alexia Pauline Delorey and Mahmoud Khalil and Nancy Fulda and David Wingate},
journal= {arXiv preprint arXiv:2203.11364},
year = {2022}
}