I am a Ph.D. candidate at Purdue University, working on Natural Language Understanding with Dr. Julia Taylor Rayz at the AKRaNLU Lab. My research focuses on semantics and reliability in large language models. The two areas I am working on are:
- Calibration in large language models during model training and fine-tuning
- Incorporating structured knowledge within computational models of language
During Summer 2022, I got the wonderful opportunity to work as a Research Intern at the Knowledge, Reasoning and Language group at Microsoft Research, working on document template discovery and structure understanding.
For more information regarding my work, please check out my Google Scholar.
Recent Updates
- April 2023 - Paper accepted at the Annual Conference of the North American Fuzzy Information processing Society NAFIPS 2023, on ‘Calibration Error Estimation Using Fuzzy Binning’
- March 2023 - Presented poster at CERIAS Information Security Symposium 2023, on ‘Text Augmentation: Improving Classification Accuracy at the Expense of Calibration?’
- Feb 2023 - Participated as a panelist at the International Workshop of the Society of Design and Process Science - SDPS 2023
- May 2022 - Joined Microsoft Research as a Research Intern, working with Sujay Jauhar, Bahar Sarrafzadeh and Milenko Drinic on document template discovery