STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Seong-Gyu, Park, Sohee, Lee, Jisu, Na, Hyunsik, Choi, Daeseon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!