On Almost Surely Safe Alignment of Large Language Models at Inference Time
Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer et al.
Action editor: Lingpeng Kong
@tmlr-pub.bsky.social@tmlr-pub.bsky.social
@tmlr-pub.bsky.socialOn Almost Surely Safe Alignment of Large Language Models at Inference Time
Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer et al.
Action editor: Lingpeng Kong