Published on

Paraphrasing with Large Language Models


This paper was accepted to the WNGT workshop at EMNLP-IJCNLP-2019 in Hong Kong.


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.

Poster Version

EMNLP-IJCNLP-2019 WNGT poster thumbnail

And the BiBTeX entry for the arXiv version:

  author       = {Sam Witteveen and
                  Martin Andrews},
  title        = {Paraphrasing with Large Language Models},
  journal      = {CoRR},
  volume       = {abs/1911.09661},
  year         = {2019},
  url          = {},
  eprinttype    = {arXiv},
  eprint       = {1911.09661},
  timestamp    = {Tue, 03 Dec 2019 14:15:54 +0100},
  biburl       = {},
  bibsource    = {dblp computer science bibliography,}