I am a fifth year Computer Science PhD student in the MURGe Lab (part of the bigger UNC NLP Lab) at the University of North Carolina at Chapel Hill, advised by Prof. Mohit Bansal. My PhD is supported by a Google PhD Fellowship and previously, by a Rebecca and Munroe Cobey Fellowship.
I study Machine Learning and NLP. Broadly, I am interested in developing language agents that can perform complex, multi-step reasoning tasks (often referred to as the System 2 Reasoning). Below are some of the main topics that I’ve worked on (publications here):
- Reasoning in Multi-Agent systems
- Large Language Model Evaluation
- Attributable Generative Reasoning
- Structured Reasoning over Implicit Knowledge
- Deductive Reasoning
During my PhD, I have spent three wonderful summers, twice interning at FAIR Labs, AI at Meta and once at Salesforce AI Research. Before starting my PhD, I was a Research Engineer at IBM Research - India building industry-scale Intelligent Tutoring Systems. Even before that, I did my M.Tech. in CS from IIT, Delhi, where I was awarded with the best Master’s thesis.
- October 2023: New pre-print from my FAIR Internship on Branch-Solve-Merge for improving LLM Evaluation and Generation.
- October 2023: ReCEval on evaluating CoT rationales is accepted to EMNLP 2023.
- September 2023: New pre-print out! Diverse LLMs improve reasoning via multi-round discussion and convincing each other.
- September 2023: Can Language Models Teach Weaker Agents is accepted to NeurIPS 2023.
- June 2023: New pre-print on Can Language Models Teach Weaker Agents out on arXiv.
- May 2023: Started Internship at FAIR Labs, hosted by Xian Li and Omer Levy.
- May 2023: MURMUR is accepted to ACL Findings.