About Me
Applied Scientist at Amazon
I specialize in solving complex natural language processing and retrieval problems and am currently working on large-scale conflict detection in heterogeneous documents and calculating agent readiness scores for documents.
Previously, I was a Machine Learning Scientist at Expedia, where I worked on introducing diversity and personalization in ranking for the text search team.
During my PhD, I built an LLM specializing in privacy policies and designed and developed PrivaSeer, a one-of-a-kind search engine indexed on over 4 million privacy policies (https://privaseer.ist.psu.edu).
More recently, I have been exploring multilingual NLP research grounded in a human-centered approach to building AI systems that are transparent, responsible, and aligned with real user needs.
News
2026
🚀 I joined Amazon as an Applied Scientist, working on large-scale conflict detection in heterogeneous documents and agent readiness scoring!
Our paper PseudoSeer: a Search Engine for Pseudocode was accepted at Findings of ACL 2026.
2025
Our paper SoAC and SoACer: A Sector-Based Corpus and LLM-Based Framework for Sectoral Website Classification was accepted at DocEng 2025.
Our paper Exposing AI Bias by Crowdsourcing: Democratizing Critique of Large Language Models was accepted at AIES 2025.
2024
🌍✈️ I joined the text search team @ Expedia as a Machine Learning Scientist!!
I was selected to be a Liberatory Tech Scholar!! 🎉
🏆 I was the out-of-the-box winner of the bias-a-thon competition conducted by the Center for Socially Responsible Artificial Intelligence.
2023
🏆 Our paper The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis won the outstanding paper award at EMNLP 2023!
🏆 Our paper Privacy Lost and Found: An Investigation at Scale of Web Privacy Policy Availability won the best student paper at DocENG 2023!
We started a blog called Beyond Words and Algorithms where we share our research insights on ML and HCI.
🏆 Our paper Researchers’ Experiences in Analyzing Privacy Policies: Challenges and Opportunities won the best student paper at PETS 2023!
🏆 Our paper Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models at ACL 2023 won the best paper award!
2022
Our paper A Study of Implicit Language Model Bias Against People With Disabilities was accepted at COLING 2022.
I started working at Trustpage as a machine learning intern and worked on question answering and semantic similarity problems.
PhD milestone cleared: Comprehensive examination. I am now ABD!