I am Rachit, an incoming PhD student at Harvard University. Broadly, I am interested in making language models useful, controllable, and accessible. I am also interested in robust evaluation and analysis.

Over the past few years, I walked my first baby steps as a researcher owing to some wonderful people and collaborations. Most recently, I was a pre-doctoral researcher at Google DeepMind, working on modularizing LLMs with Partha and Prateek. Before that, 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 was fortunate to collaborate with Danish for more than two years to evaluate explanation methods in NLP¹. I also had an amazing time working 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.

News and Timeline

2024

• August Starting my doctorate at Harvard University!
• May Presenting our work on composing large language models at ICLR 2024 in Vienna!

2023

• May Presenting our work on linear mode connectivity at ICLR 2023 in Kigali!

2022

• September My bachelor’s thesis work done at the Technion was accepted at NeurIPS 2022!
• August Joining Google Research India as a pre-doctoral researcher.
• June Releasing the pre-print for our work on analyzing linear mode connectivity and out-of-distribution behaviour. Led by Jeevesh and mentored by Naomi.
• May Two papers on commonsense and factual reasoning done at Adobe MDSR accepted at NAACL 2022!
• January Starting my bachelor’s thesis with Yonatan at the Technion, Israel!

2021

• November After a year-long review and revision process, our work evaluating model explanations has been accepted at TACL. In collaboration with Danish.
• July Attending the 11th Lisbon Machine Learning Summer School (LXMLS 2021).
• May Work with CDLI accepted at ACL SRW 2021. Gauging machine translation and sequence labeling for extremely low-resource languages.
• May Starting as a Research Intern at Adobe’s Media and Data Science Research (MDSR).

2020

• November Started collaborating with Danish (LTI, CMU) on evaluating neural explanations for NLP.
• June Contributing to the Cuneiform Digital Library Initiative (CDLI) as a part of GSoC!