作者

Diyi Yang

Natural Language Processing

2025-11-12 至 2025-11-12 共收录 1 篇

2505.11770 2025-11-12 cs.LG cs.AI cs.CL stat.ML

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors

Jing Huang, Junyi Tao, Thomas Icard, Diyi Yang, Christopher Potts

机构 * stanford（斯坦福大学）

Comments ICML 2025

↑