Aaron Mueller

Aaron Mueller


Zuckerman postdoctoral fellow working with Yonatan Belinkov and David Bau on interpretability and robustness in language models.

Email: λ@northeastern.edu, where λ=aa.mueller

About

I am interested in evaluating and improving the robustness of NLP systems. My work spans causal, behavioral, and mechanistic interpretability methods; targeted model editing; and evaluations of the linguistic abilities and inductive biases of pre-trained language models. I am also interested in improving the sample-efficiency of language models.

I completed by Ph.D. in Computer Science at the Center for Language and Speech Processing at Johns Hopkins University under the supervision of Tal Linzen and Mark Dredze. My dissertation analyzed the behaviors and mechanisms underlying emergent syntactic abilities in neural language models. My Ph.D. studies were supported by a National Science Foundation Graduate Research Fellowship.

I completed my B.S. in Computer Science and B.S. in Linguistics at the University of Kentucky, where I was a Gaines Fellow and Patterson Scholar. My thesis, which focused on neural machine translation for low-resource French dialects, was advised by Ramakanth Kavuluru and Mark Richard Lauersdorf.


News

Upcoming

Presenting a paper at NAACL

Upcoming

Invited talks at Maastricht, Saarland, and EPFL

2024/04

Invited talk at UCSB

2024/03

New preprint! We propose sparse feature circuits to discover and edit mechanisms of LM behavior.

2024/03

Invited talk at Nokia Bell Labs

2024/02

Invited talks at Brown University and University of Pittsburgh

2024/01

Our paper on function vectors was accepted to ICLR

2023/12
2023/12

The Inverse Scaling Prize was featured in TMLR

2023/11

New preprint: in-context learning yields different behaviors on ID vs. OOD examples

2023/07

Our paper received an outstanding paper award

2023/07

4 papers at ACL. See you in Toronto!

2023/05

The BabyLM Challenge was featured in the New York Times

2023/01

Organizing the BabyLM Challenge

2022/12

Invited talks at Bar-Ilan University and the Technion

2022/12

Presented a paper at CoNLL