English

Get the gist? Using large language models for few-shot decontextualization

Computation and Language 2023-10-11 v1 Artificial Intelligence

Abstract

In many NLP applications that involve interpreting sentences within a rich context -- for instance, information retrieval systems or dialogue systems -- it is desirable to be able to preserve the sentence in a form that can be readily understood without context, for later reuse -- a process known as ``decontextualization''. While previous work demonstrated that generative Seq2Seq models could effectively perform decontextualization after being fine-tuned on a specific dataset, this approach requires expensive human annotations and may not transfer to other domains. We propose a few-shot method of decontextualization using a large language model, and present preliminary results showing that this method achieves viable performance on multiple domains using only a small set of examples.

Keywords

Cite

@article{arxiv.2310.06254,
  title  = {Get the gist? Using large language models for few-shot decontextualization},
  author = {Benjamin Kane and Lenhart Schubert},
  journal= {arXiv preprint arXiv:2310.06254},
  year   = {2023}
}
R2 v1 2026-06-28T12:45:25.397Z