About me

I am Neeraja Kirtane. I am a second-year MSCS student at the University of Illinois Urbana Champaign. I am currently advised by Prof. Hao Peng and closely collaborating with Prof. Dilek Hakkani-Tür. My current research interests lie in making NLP models trustworthy and interpretable. Recently I worked on preemptively detecting and mitigating hallucinations in LLMs by analysing the hidden states of the model (link). I am also working on jailbreaking LLMs to produce harmful content (link).

Previously, I was a Post Baccalaureate fellow at the Robert Bosch Centre for Data Science and AI RBCDSAI, IITM Chennai. I was advised by Prof. Balaraman Ravindran and worked on building automated ML tools to generate wikipedia biographies for notable women in STEM. I completed my undergraduate studies in Computer Science and Engineering from Manipal Institute of Technology in Manipal, Karnataka, India.

If you like my work or want to collaborate with me, you can get in touch with me via Email or LinkedIn. Check out my work in my CV

I am looking for job opportunities in AI safety applications. If you feel I am a right fit, please contact me.