When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Hanqi, Xu, Hainiu, Qi, Siya, Yang, Shu, He, Yulan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!