News

• I will be joining Hugging Face working on model understanding and evaluation 🤗
• Robustly extracting factual information from LLMs via prompts accepted at ICLR 2022!
• Invited panelist for the CATT 2021 Global Analytics Summit on Explainable AI
• Co-hosting knowledge enriched NLG tutorial at EMNLP '21
• ICML UDL workshop talk on Evaluating deep learning models with applications to NLP
• Invited talk EMNLP '21 SustaiNLP workshop
• SummVis accepted as ACL '21 demo paper
• Robustness Gym accepted as NAACL '21 demo paper
• We announced Robustness Gym .
• 2 papers accepted at ICLR 2021!

I am a Research Scientist at Hugging Face 🤗 My interests and expertise lie at the intersection of Model Evaluation, Robustness, and Interpretability. My long term research agenda includes 1. Data programming for understanding training data, 2. Human-in-the-loop training and evaluation for model robustness, 3. Repurposing LLMs and PLMs to make them more usable in the real world.

Before joing Hugging Face, I was a Research Scientist at Salesforce Research where I worked with Richard Socher and Caiming Xiong on commonsense reasoning and interpretability in NLP. I led a small team focused on building robust natural language generation models. Prior to working at Salesforce, I completed my Ph.D. thesis in the Department of Computer Science at the Machine Learning Research Group of the University of Texas, Austin. I worked with my advisor Prof. Ray Mooney on problems in NLP, Vision and at the intersection of NLP and Vision. I have also worked on problems in Explainable AI (XAI) wherein I proposed a scalable approach to generate visual explanations for ensemble methods using the localization maps of the component systems. Evaluating explanations is also a challenging problem and I proposed two novel evaluation metrics that does not require human generated GT.

I completed my MS in CS with thesis advised by Jason Baldridge on new topic detection using topical alignment from tweets based on their author and recipient.