A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Hui, Zeng, Yifan, Wu, Yue, Wang, Huazheng, Wang, Mengdi, Leqi, Liu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.13828