EPA: Easy Prompt Augmentation on Large Language Models via Multiple Sources and Multiple Targets

TL;DR

EPA is a novel method that automatically augments prompts with paraphrased demonstrations from multiple sources and targets, reducing user effort and enhancing large language model performance across diverse NLP tasks.

Contribution

EPA introduces an automatic prompt augmentation technique using paraphrasing to improve LLM performance without requiring manual demonstration writing.

Findings

EPA improves performance on NLU and NLG tasks.

EPA enhances translation quality across multiple languages.

EPA reduces user effort in prompt construction.

Abstract

Large language models (LLMs) have shown promising performance on various NLP tasks via task prompting. And their performance can be further improved by appending task demonstrations to the head of the prompt. And usually, a better performance can be achieved with more demonstrations. However, asking the users to write the demonstrations can be cumbersome. As a simple yet cost-effective workaround, this paper proposes a novel method called EPA (\textbf{E}asy \textbf{P}rompt \textbf{A}ugmentation)\footnote{While this paper considers augmenting prompts via demonstrations, we name it EPA as the name EDA is already taken by a well-known NLP method \citep{wei-zou-2019-eda}.} that effectively minimizes user efforts in writing demonstrations while improving the model performance at the same time. EPA achieves these goals by automatically augmenting the demonstrations with multiple sources/targets, where each of them paraphrases each other. This is well motivated as augmenting data via paraphrasing effectively improves neural language models. EPA thus employs paraphrasing as an augmentation method for in-context learning. Extensive experiments indicate that EPA effectively improves both NLU and NLG tasks, covering from natural language inference to machine translation in translating tens of languages.\footnote{Code and data will be released upon publication.}