Vin Howe

Twitter · Google Scholar · GitHub · LinkedIn · vin @ this domain

I’m a Master's student in computer science at Brigham Young University, having recently completed a Bachelor's in BYU's Applied and Computational Mathematics program. I work with David Wingate in his Perception, Control, and Cognition Lab, where I study language models broadly.

I built a chatroom that used large language models to improve polarizing political conversations. My group published a paper about it in PNAS.

Research Interests

I’m broadly interested in NLP and large language models. Right now, I’m studying what kinds of useful inductive biases self-supervision fails to induce even after training on trillions(!) of tokens of natural language data.

Publications

2024

Diagram of gradient sparse autoencoder (gSAE) Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
Jeffrey Olmo, Jared Wilson, Max Forsey, Bryce Hepner, Thomas V Howe, David Wingate
Findings of the Association for Computational Linguistics

2023

Preview of chatroom Leveraging AI for democratic discourse: Chat interventions can improve online political conversations at scale
Lisa P Argyle, Christopher A Bail, Ethan C Busby, Joshua R Gubler, Thomas V Howe, Christopher Rytting, Taylor Sorensen, David Wingate
Proceedings of the National Academy of Sciences