👩🏻💻 I'm a CS PhD candidate at UIUC's Conversational AI Lab, advised by Prof. Dilek Hakkani-Tür.
🔬 My research focuses on LLM alignment, evaluation, and safety — figuring out when, how, and why language models become sycophant, biased, or deceptive, and how to fix them.
📫 Reach me at: rabbani8@illinois.edu
🌐 Website · Google Scholar · LinkedIn
🗣️ DialDefer — measuring LLM judgment shift based on who's talking, not what's being said
💬 From Fact to Judgment — investigating task framing effects on LLM conviction (IWSDS'26)
My baby Blu 💙


