This paper proposes a framework to train dense retrievers that can identify high-quality in-context examples for large language models (LLMs), improving their learning performance. Experimental results show significant enhancements in performance and generalization ability to unseen tasks.

https://arxiv.org/abs//2307.07164

YouTube: https://www.youtube.com/@ArxivPapers

PODCASTS:

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers