Paraphrasing with Large Language Models

TL;DR

This paper introduces a technique leveraging large language models like GPT-2 to generate high-quality paraphrases for sentences and longer texts without chunking, enhancing NLP applications.

Contribution

It presents a novel method for using large language models to perform effective paraphrasing on various text lengths without segmentation.

Findings

Capable of paraphrasing sentences and paragraphs

Maintains high quality in generated paraphrases

Operates without breaking texts into chunks

Abstract

Recently, large language models such as GPT-2 have shown themselves to be extremely adept at text generation and have also been able to achieve high-quality results in many downstream NLP tasks such as text classification, sentiment analysis and question answering with the aid of fine-tuning. We present a useful technique for using a large language model to perform the task of paraphrasing on a variety of texts and subjects. Our approach is demonstrated to be capable of generating paraphrases not only at a sentence level but also for longer spans of text such as paragraphs without needing to break the text into smaller chunks.