无真值标记的信息提示工程工程方法
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
摘要：
预先训练的语言模型从它们所训练的大量语料库中获得大量的语言和事实知识，并且提示工程试图将这些模型与特定任务相匹配。不幸的是，现有的提示工程方法需要大量的标记数据，访问模型参数，或两者兼而有之。本文介绍了一种新的选择提示模板\textit{without labeled examples}和\textit{without direct access to the model}的方法。具体来说，在一组候选模板，我们选择的模板，最大化的互信息之间的输入和相应的模型输出。在8个数据集，代表7个不同的NLP任务，我们表明，当一个模板具有高互信息，它也有高精度的任务。在最大的模型上，使用我们的方法选择提示可以获得从平均提示准确度到最佳提示准确度的90%，并且不需要真值标签。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
