Aryaman Arora papers blog projects

Search IconIcon to open search

Hi! I'm Aryaman.

I am a first-year Ph.D. student at Stanford NLP advised by Dan Jurafsky and Christopher Potts.

I work on interpretability because I want to understand how neural networks (esp. language models) work. I believe that this is an achievable goal. Some things I’ve been thinking about:

  • How can we ensure that causal explanations are actually faithful to the model’s behavior? We need theory, benchmarks, metrics, etc.
  • In a deep learning world, can linguistics still be useful in guiding how we do interpretability on language models?
  • Can interpretability provide actionable findings that help us make better models?

Machine learning is still alchemy, and I think it would be cool if we could turn it into a science. To that end, I am inspired by work in NLP, causal inference, information theory, and psycholinguistics.

If you want to chat about research, feel free to send me an email (aryamana [at] stanford [dot] edu)!

# Selected papers

See more.

# More about me

I was born in New Delhi, India, raised in Savannah, Georgia (the U.S. state), and I think of home as Washington, D.C.—where I spent part of high school and my undergrad.

Before coming to Stanford to start my Ph.D. in 2023, I completed my B.S. in Computer Science and Linguistics at Georgetown University. There, I was mentored by Nathan Schneider as a member of his research group NERT. In those days, I primarily worked on computational linguistics and did a lot of linguistic annotation for Indian languages. Regardless of what I work on now, my research style is probably largely copied from Nathan’s.

Since 2021, I have also been closely working with Ryan Cotterell at ETH Zürich on information theory, and I visited Switzerland in Summer 2021 and 2023. From working with Ryan, I learned to be a little less scared of math.

In 2022, I spent the summer at Apple in Seattle with Robert Daland working on evaluating robustness on a ton of languages for Siri, and winter at Redwood Research in Berkeley on mechanistic interpretability.

My research interests pivoted significantly in late 2022 towards interpretability, but I still have a love for language(s).

My résumé and blog should tell you a little more.

# News

  • 2023-09-14: Moved to the San Francisco Bay Area 🌉 to start my Ph.D.
  • 2023-07-31: Back from the Leiden University Summer School in Languages and Linguistics in the Netherlands!
  • 2023-02-08: Accepted to the Ph.D. program at Stanford CS!