I’m a 4th year Computer Science Ph.D. student at Virginia Tech advised by Dr. Chandan Reddy. My research interests fall broadly under the umbrella of trustworthy and responsible AI with a focus on fairness, interpretability, and robustness of deep learning models – particularly in the domain of natural language processing (NLP). I work on identifying vulnerabilities of large language models (LLMs) and building systems that are fair, interpretable, and robust to adversarial perturbations in the input.
Prior to starting my Ph.D., I was a research intern at the University of Michigan, Ann Arbor where I worked with Dr. David Jurgens and Dr. Libby Hemphill on identifying offensive comments and de-escalating conflicts on social media platforms. I also worked briefly as a software engineer at Intuit, India. Before that, I completed my MS by research in Computational Lingiustics and Bachelors in Computer Science from IIIT, Hyderabad, India.
- May 2023: Started a research internship with the Responsible AI org at Google Research in sunny California!
- May 2023: Our paper SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models was accepted at ACL 2023.
- January 2023: Our paper Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis was accepted at EACL (Findings) 2023.
- November 2022: Our paper CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models was accepted at AAAI 2023.