English

Paraphrasing with Large Language Models

Computation and Language 2019-11-22 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1911.09661,
  title  = {Paraphrasing with Large Language Models},
  author = {Sam Witteveen and Martin Andrews},
  journal= {arXiv preprint arXiv:1911.09661},
  year   = {2019}
}

Comments

Accepted paper for WNGT workshop at EMNLP-IJCNLP 2019. (7 pages including references and supplemental material)

R2 v1 2026-06-23T12:23:44.763Z