Swarnadeep Saha

Swarnadeep Saha

PhD student at UNC-NLP. Interested in Large Language Models, Reasoning, Planning

About Me

In the Fall, I will join FAIR Labs, Meta as a Research Scientist to work with Dr. Jason Weston.

I recently obtained a PhD in Computer Science from 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 was supported by a Google PhD Fellowship and 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 and planning tasks (often referred to as the System 2 Reasoning). I see human language as the ideal medium for reasoning, communication, and collaboration among agents. Below are some of the main topics that I’ve worked on (publications here):

  1. Reasoning and Planning in Multi-Agent systems
  2. Large Language Model Evaluation
  3. Attributable Generative Reasoning
  4. Structured Reasoning over Implicit Knowledge
  5. 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.

Email: swarna@cs.unc.edu

Recent News