This paper introduces a method, MIN-K% PROB, to detect if a large language model was trained on a given text without knowing the pretraining data. It achieves better results than previous methods and is effective in various real-world scenarios.

https://arxiv.org/abs//2310.16789

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