Pardis Sadat Zahraei
PardisSzah
AI & ML interests
None yet
Recent Activity
authored a paper about 15 hours ago
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness authored a paper about 15 hours ago
AgentAbstain: Do LLM Agents Know When Not to Act? authored a paper about 15 hours ago
I Am Aligned, But With Whom? MENA Values Benchmark for Evaluating Cultural Alignment and Multilingual Bias in LLMs