Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xinyue, Mireshghallah, Niloofar, Ginsburg, Jane C., Chakrabarty, Tuhin
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.20957