I am a Ph.D. candidate at Purdue University, working on Natural Language Understanding with Dr. Julia Taylor Rayz at the AKRaNLU Lab. My work focuses on enhancing language model reasoning by addressing challenges in resolving linguistic ambiguity and enhancing generalization, particularly in cases where the structural form (locution) diverges from the communicative function, such as in manipulative discourse.
During my PhD, I have worked on quantifying how alignment methods can exacerbate countervailing biases, demonstrated that calibrated models lack generalizability, developed methods for sense-enrichment of contextualized representations, worked on fuzzy models for intent classification, including task-based intent as well as covert malicious intents.
Currently, I am finalizing my dissertation on Reliable Detection of Manipulative Discourse
. My research takes a two-pronged approach:
For more information regarding my work, please check out my Google Scholar.
Recent Updates