I am Rachit, a pre-doctoral researcher at Google Research India working with Partha. I am interested in making language models useful, controllable, and accessible. I am also interested in robust evaluation and analysis. Previously, I was an undergraduate student at the Delhi Technological University.

Over the past few years, I walked my first baby steps as a researcher owing to some wonderful people and collaborations. I pursued my bachelor’s thesis research with Yonatan at the Technion in Israel. There I had a great time studying how intrinsic properties of a neural network are informative of generalization behaviours. Before that, I was a research intern at Adobe’s Media and Data Science Research Lab, where I worked on commonsense reasoning for large language models.

I am extremely fortunate to have been involved in some incredible collaborations. I worked with Danish for more than two years to evaluate explanation methods in NLP1. I also worked with Naomi studying mode connectivity in loss surfaces of language models2.

I also spent a couple of wonderful summers as a part of the Google Summer of Code program with the Cuneiform Digital Library Initiative (CDLI). Here, I was advised by Jacob and Niko. My first exposure to research was at LCS2, IIIT-D.

News and Timeline

🎓 I am actively looking for Ph.D. positions for Fall 2024!





  1. Started with a meek awe-inspired email 

  2. Started with a message on MLC’s Discord channel