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

arXiv: https://arxiv.org/abs/2310.06254 · HTML: https://mlsanity.com/paper/2310.06254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 5 of 5)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)

## Abstract (arXiv)

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.