This paper surveys the emerging field of knowledge editing in deep neural networks, which aims to enable efficient and effective changes to pre-trained models without affecting previous tasks. It reviews relevant approaches and outlines potential future directions.

https://arxiv.org/abs//2310.19704

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

TikTok: https://www.tiktok.com/@arxiv_papers

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

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