Hi there! My name is Anirudh, and I use he/him pronouns. I am an incoming Ph.D. student in Computer Science at Cornell University, where I will be advised by Prof. Tanya Goyal. My research interests are primarily in the field of Natural Language Processing. Some of the research directions I’m especially excited about include:

1. Factuality – Ensuring trustworthiness and mitigating hallucinations by encouraging more causal inferences and fewer guesses, particularly in long-context and long-form text generation tasks.
2. Instruction-following ability of LLMs.
3. Personalization, creativity, and human–AI collaboration - How can we improve and evaluate creativity and personalization in LLM-generated text, and design better collaboration strategies that understand user preferences and intentions?
4. Building sustainable and reliable evaluation frameworks to test modern LLMs on the above aspects.

Previously, I completed my master's degree in Computer Science at UMass Amherst. There, I was fortunate to collaborate with Prof. Mohit Iyer on studying the impact of LLM quantization on long-context and long-form text generation scenarios, and with Dr. Haw-Shiuan Chang and Prof. Hamed Zamani, on evaluating creativity and instruction-following ability in LLMs. Even earlier, I graduated from BITS Pilani, India, with a dual major: B.E. in Computer Science and M.Sc. in Mathematics. As part of my undergraduate thesis, I worked for over a year with Prof. Subrata Chakraborty at the University of New England, Australia, on projects involving computer vision for healthcare (such as medical image analysis, autism detection, and psychological testing).