QCRI-UIUC

AI & ML interests

None defined yet.

Recent Activity

PardisSzah  authored a paper 18 days ago

Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness

PardisSzah  authored a paper 18 days ago

AgentAbstain: Do LLM Agents Know When Not to Act?

PardisSzah  authored a paper 18 days ago

I Am Aligned, But With Whom? MENA Values Benchmark for Evaluating Cultural Alignment and Multilingual Bias in LLMs

View all activity

Team members 2