From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Mengru, Xu, Zhenqian, Fang, Junfeng, Yao, Yunzhi, Deng, Shumin, Chen, Huajun, Zhang, Ningyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!