I am a first year CS PhD student at Khoury College of Computer Science at Northeastern University in Boston. I am advised by Prof Mai ElSherief.
Before starting my PhD, I was a Software Engineer with the Selection Monitoring and Catalog Systems organization at Amazon in Seattle. Prior to that I was an MS CS student at Georgia Tech. At Georgia Tech, I was advised by Prof Srijan Kumar in the CLAWS Lab. I also dabble as a Research mentor with SimPPL.
I am focused on understanding, evaluating, and aligning AI for social good and downstream applications. My work, primarily centered around NLP, can be broadly categorized into the following areas:
How do models align to humans in context of value-based artifacts?
In pursuit of this, I have studied how dialectal features added as a form of implicit identity for a culture can expose systemic biases of an LLM (SafeGenAI Oral Presentation @ NeurIPS’24), and have studied how LLMs interpret different genders and races when viewed as professions.My current work focusses on evaluating models on a value based axis using tasks as emotional intelligence. [In submission at COLM’25]
Methadologically, using Value Based Alignment as a proposition, my work explores the addition of a user’s persona to the LLM’s context.
How can we understand and support the well-being of online communities?
I am interested in leveraging AI capabilities for understanding how communities – specifically those cultivated online function. I have worked in understanding how misinformation can be countered using field studies on Twitter (now X). I have analysed hate speech categories and reasoning and worked on a report classifying dog whistles on social media.
Teaching
TA for CS 4100: Foundations of AI (Spring 2025) with Prof Chris Amato
TA for CS 3600: Intro to AI, with Prof James Rehg (Spring 2022) and Prof Mark Reidl (Fall 2022)
Talks
Slides of my lecture on Advanced Topics in AI
Presentation and Slides at SafeGenAI workship at NeurIPS on Who Speaks Matters: Analysing the Influence of the Speaker’s Ethnicity on Hate Classification