Aryaman Arora · आर्यमन अरोरा
I am a third-year Ph.D. student at Stanford University advised by Dan Jurafsky and Christopher Potts, and funded by the NSF Graduate Research Fellowship Program.
I work on interpretability of language models. I believe understanding how language models work is the scientific problem of our age.
I completed my B.S. in Computer Science and Linguistics at Georgetown University, where I worked with Nathan Schneider on computational linguistics. I interned at ETH Zürich with Ryan Cotterell, as well as at Apple, Redwood Research, and (most recently) Transluce.
Contact
Google Scholar · GitHub · Twitter · Email
Greatest Hits [» more papers]
ADAG: Automatically describing attribution graphs
Language model circuits are sparse in the neuron basis
Mechanistic evaluation of Transformers and state space
models
AxBench: Steering LLMs? Even simple baselines outperform sparse
autoencoders
ReFT: Representation finetuning for language models
CausalGym: Benchmarking causal interpretability methods on
linguistic tasks