Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
Paper • 2604.10681 • Published
Vu Truong
Vincent171
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models updated a model over 2 years ago
Vincent171/distilBerd_arg updated a model over 2 years ago
Vincent171/finetuning-sentiment-model-3000-samplesOrganizations
None yet
authored a
paper 2 days ago