BackdoorLLM

AI & ML interests

Trustworthy ML/AI

Recent Activity

hanxunh  authored a paper 12 days ago

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

hanxunh  authored a paper about 1 month ago

VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs

hanxunh  authored a paper about 2 months ago

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

View all activity

Team members 4