Paraphrasing with Large Language Models
This provides a useful technique for NLP practitioners needing to paraphrase text, though it appears incremental as it applies existing models to a known task.
The authors tackled the problem of paraphrasing text using large language models, demonstrating that their approach can generate paraphrases for both sentences and entire paragraphs without chunking.
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.