Hey there! I am a Senior studying Computer Science at UC Berkeley. Previously, I spent a great summer with the AI Technology Group at the MIT Lincoln Lab, working with Keegan Quigley and Miriam Cha. Currently, I am an undergraduate researcher in the Berkeley NLP Group, where I have been very fortunate to collaborate with and learn from Alane Suhr, Sanjay Subramanian, Kayo Yin, and Dan Klein.

My research interests broadly span natural language processing, with a focus on improving our understanding of models through interpretability and evaluation. Recently, I have been exploring the multilingual capabilities of LLMs and the training dynamics of language models.

Preprints & Publications

Using Language Models to Disambiguate Lexical Choices in Translation
Josh Barua, Sanjay Subramanian, Kayo Yin, Alane Suhr
EMNLP 2024
paper| code

Bidirectional Captioning for Clinically Accurate and Interpretable Models
Keegan Quigley, Miriam Cha, Josh Barua, Geeticka Chauhan, Seth Berkowitz, Steven Horng, Polina Golland
Under Review
paper| cite