MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dékány, Csaba, Balauca, Stefan, Staab, Robin, Dimitrov, Dimitar I., Vechev, Martin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence I.2.7; K.4.1
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.16947