Language Models Resist Alignment: Evidence From Data Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Jiaming, Wang, Kaile, Qiu, Tianyi, Chen, Boyuan, Zhou, Jiayi, Li, Changye, Lou, Hantao, Dai, Juntao, Liu, Yunhuai, Yang, Yaodong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!