LLM-Tuning-Safety

AI & ML interests

None defined yet.

Recent Activity

vtu81  authored a paper 6 months ago

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors

vtu81  authored a paper 6 months ago

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

vtu81  authored a paper 6 months ago

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

View all activity

Team members 4