Publications

Please see my Google Scholar page for an up-to-date list.

Preprints & In Submission

• The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
  Sankaran Vaidyanathan, David Arbour, Aaron Mueller, Scott Niekum, David Jensen. arXiv preprint. [paper]

• Pitfalls in Evaluating Interpretability Agents
  Tal Haklay, Nikhil Prakash, Sana Pandey, Antonio Torralba, Aaron Mueller, Jacob Andreas, Tamar Rott Shaham, Yonatan Belinkov. arXiv preprint. [paper]

• Mechanisms of AI Protein Folding in ESMFold
  Kevin Lu, Jannik Brinkmann, Stefan Huber, Aaron Mueller, Yonatan Belinkov, David Bau, Chris Wendler. arXiv preprint. [paper]

• In-context Learning Without Copying
  Kerem Sahin, Sheridan Feucht, Adam Belfki, Jannik Brinkmann, Aaron Mueller, David Bau, Chris Wendler. arXiv preprint. [paper] [code]

Peer-reviewed Articles

2026

• From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
  Aaron Mueller, Andrew Lee, Shruti Joshi, Ekdeep Singh Lubana, Dhanya Sridhar, Patrik Reizinger. Association for Computational Linguistics (ACL). [paper]

• Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
  John Seon Keun Yi, Aaron Mueller, Dokyun Lee. Association for Computational Linguistics (ACL). [paper]

• Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
  Deniz Bayazit, Aaron Mueller, Antoine Bosselut. Association for Computational Linguistics (ACL). [paper] [code]

• CRISP: Persistent Concept Unlearning via Sparse Autoencoders
  Tomer Ashuach, Dana Arad, Aaron Mueller, Martin Tutek, Yonatan Belinkov. Association for Computational Linguistics (ACL). [paper]

• Do Language Models Track Entities Across State Changes?
  Zilu Tang, Qiao Zhao, Gabriel Franco, Derry Wijaya, Aaron Mueller, Sebastian Schuster, Najoung Kim. International Conference on Machine Learning (ICML). [paper]

• Causality is Key for Interpretability Claims to Generalise
  Shruti Joshi, Aaron Mueller, David Klindt, Wieland Brendel, Patrik Reizinger, Dhanya Sridhar. International Conference on Machine Learning (ICML). [paper]

• BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
  Shengao Wang, Wenqi Wang, Zecheng Wang, Max Whitton, Michael Wakeham, Arjun Chandra, Joey Huang, Pengyue Zhu, Helen Chen, David Li, Jeffrey Li, Shawn Li, Andrew Zagula, Amy Zhao, Andrew Zhu, Sayaka Nakamura, Yuki Yamamoto, Jerry Jun Yokono, Aaron Mueller, Bryan A. Plummer, Kate Saenko, Venkatesh Saligrama, Boqing Gong. Conference on Computer Vision and Pattern Recognition (CVPR). [paper]

• Priors in Time: Missing Inductive Biases for Language Model Interpretability
  Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur, Valerie Costa, Greta Tuckute, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Daniel Wurgaft, Eric J. Bigelow, Johnny Lin, Demba Ba, Martin Wattenberg, Fernanda Viegas, Melanie Weber, Aaron Mueller. International Conference on Learning Representations (ICLR). [paper] [code]

• Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?
  Zhengyang Shan, Aaron Mueller. European Chapter of the Association for Computational Linguistics (EACL). [paper]

• Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection
  Joe Stacey, Lisa Alazraki, Aran Ubhi, Beyza Ermis, Aaron Mueller, Marek Rei. European Chapter of the Association for Computational Linguistics (EACL). [paper] [code]

• The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis
  Aaron Mueller, Jannik Brinkmann, Millicent Li, Samuel Marks, Koyena Pal, Nikhil Prakash, Can Rager, Aruna Sankaranarayanan, Arnab Sen Sharma, Jiuding Sun, Eric Todd, David Bau, Yonatan Belinkov. Computational Linguistics. [paper]

2025

• SAEs Are Good for Steering – If You Select the Right Features
  Dana Arad, Aaron Mueller, Yonatan Belinkov. Empirical Methods in Natural Language Processing (EMNLP). [paper] [code]

• Bigger is not always better: The importance of human-scale language modeling for psycholinguistics
  Ethan Gotlieb Wilcox, Michael Hu, Aaron Mueller, Tal Linzen, Alex Warstadt, Leshem Choshen, Chengxu Zhuang, Ryan Cotterell, Adina Williams. Journal of Memory and Language (JML). [paper]

• MIB: A Mechanistic Interpretability Benchmark
  Aaron Mueller*, Atticus Geiger*, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov. International Conference on Machine Learning (ICML). [website] [paper] [code] [data] [leaderboard]

• Position-aware Automatic Circuit Discovery
  Tal Haklay, Hadas Orgad, Aaron Mueller, Yonatan Belinkov. Association for Computational Linguistics (ACL). [paper] [code]

• Characterizing the Role of Similarity in the Property Inferences of Language Models
  Juan Diego Rodriguez, Aaron Mueller, Kanishka Misra. Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL). [paper] [code]

• Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
  Jannik Brinkmann, Chris Wendler, Christian Bartelt, Aaron Mueller. Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL). [paper] [code]

• Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
  Michael Hanna*, Aaron Mueller*. Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL). [paper] [code]

• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
  Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller. International Conference on Learning Representations (ICLR). [paper] [code]

• NNsight and NDIF: Democratizing Access to Foundation Model Internals
  Jaden Fiotto-Kaufman, Alexander R Loftus, Eric Todd, Jannik Brinkmann, Caden Juang, Koyena Pal, Can Rager, Aaron Mueller, Samuel Marks, Arnab Sen Sharma, Francesca Lucchetti, Michael Ripa, Adam Belfki, Nikhil Prakash, Sumeet Multani, Carla Brodley, Arjun Guha, Jonathan Bell, Byron Wallace, David Bau. International Conference on Learning Representations (ICLR). [paper] [website] [source]

• Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
  Yaniv Nikankin, Anja Reusch, Aaron Mueller, Yonatan Belinkov. International Conference on Learning Representations (ICLR). [paper] [code]

2024

• Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks (Honorable Mention for Top Paper)
  Aaron Mueller. Mechanistic Interpretability Workshop at the 2024 International Conference on Machine Learning. [paper]

• Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models
  Aruna Sankaranarayanan, Dylan Hadfield-Menell, Aaron Mueller. Workshop on LLMs and Cognition at the 2024 International Conference on Machine Learning. [paper]

• In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax
  Aaron Mueller, Albert Webson, Jackson Petty, Tal Linzen. North American Chapter of the Association for Computational Linguistics (NAACL). [paper] [code]

• Function Vectors in Large Language Models
  Eric Todd, Millicent L. Li, Arnab Sen Sharma, Aaron Mueller, Byron C. Wallace, David Bau. International Conference on Learning Representations (ICLR). [website] [paper] [code]

2023

• How to Plant Trees 🌳 in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases
  Aaron Mueller, Tal Linzen. Association for Computational Linguistics (ACL). [paper] [code]

• Meta-learning with Demonstration Retrieval for Efficient Few-shot Learning
  Aaron Mueller, Kanika Narang, Lambert Mathias, Qifan Wang, Hamed Firooz. Findings of the Association for Computational Linguistics (ACL). [paper]

• Language Model Acceptability Judgments Are Not Always Robust to Context (Outstanding Paper Award)
  Koustuv Sinha, Jon Gauthier, Aaron Mueller, Kanishka Misra, Keren Fuentes, Roger Levy, Adina Williams. Association for Computational Linguistics (ACL). [paper]

• Inverse Scaling: When Bigger Isn't Better (Featured Paper)
  Ian R. McKenzie, Alexander Lyzhov, Michael Martin Pieler, Alicia Parrish, Aaron Mueller, Ameya Prabhu, Euan McLean, Xudong Shen, Joe Cavanagh, Andrew George Gritsevskiy, Derik Kauffman, Aaron T. Kirtland, Zhengping Zhou, Yuhui Zhang, Sicong Huang, Daniel Wurgaft, Max Weiss, Alexis Ross, Gabriel Recchia, Alisa Liu, Jiacheng Liu, Tom Tseng, Tomasz Korbak, Najoung Kim, Samuel R. Bowman, Ethan Perez. Transactions on Machine Learning Research (TMLR). [paper]

• What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
  Julian Michael, Ari Holtzman, Alicia Parrish, Aaron Mueller, Alex Wang, Angelica Chen, Divyam Madaan, Nikita Nangia, Richard Yuanzhe Pang, Jason Phang, Samuel R. Bowman. Association for Computational Linguistics (ACL). [paper]

2022

• Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models
  Aaron Mueller, Robert Frank, Tal Linzen, Luheng Wang, Sebastian Schuster. Association for Computational Linguistics (ACL). [paper] [code]

• Label Semantic Aware Pre-training for Few-shot Text Classification
  Aaron Mueller, Jason Krone, Salvatore Romeo, Saab Mansour, Elman Mansimov, Yi Zhang, Dan Roth. Association for Computational Linguistics (ACL). [paper]

• Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models
  Aaron Mueller, Yu Xia, Tal Linzen. Conference on Computational Natural Language Learning (CoNLL). [paper] [code]

• Bernice: A Multilingual Pre-trained Encoder for Twitter
  Alexandra DeLucia, Shijie Wu, Aaron Mueller, Carlos Aguirre, Mark Dredze. Empirical Methods in Natural Language Processing (EMNLP). [paper]

2021

• Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling
  Aaron Mueller, Mark Dredze. North American Chapter of the Association for Computational Linguistics (NAACL). [paper] [poster] [code] [bib]

• Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
  Aaron Mueller*, Matthew Finlayson*, Sebastian Gehrmann, Stuart Shieber, Tal Linzen, Yonatan Belinkov. Association for Computational Linguistics (ACL). [paper] [code] [bib]

• Decoding Methods for Neural Narrative Generation
  Alexandra DeLucia*, Aaron Mueller*, Xiang Lisa Li, João Sedoc. Workshop on Generation Evaluation and Metrics (GEM), at the Association for Computational Linguistics (ACL). [paper] [code] [bib]

• Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement
  Aaron Mueller, Zach Wood-Doughty, Silvio Amir, Mark Dredze, Alicia Lynn Nobles. Proceedings of the Association for Computing Machinery (ACM) on Human-Computer Interaction (HCI), Vol. 5 (CSCW1). [paper] [bib]

2020

• Cross-Linguistic Syntactic Evaluation of Word Prediction Models
  Aaron Mueller, Garrett Nicolai, Panayiota Petrou-Zeniou, Natalia Talmina, Tal Linzen. Association for Computational Linguistics (ACL). [paper] [code] [bib]

• An Analysis of Massively Multilingual Neural Machine Translation for Low-Resource Languages
  Aaron Mueller, Garrett Nicolai, Arya D. McCarthy, Dylan Lewis, Winston Wu, David Yarowsky. Language Resources and Evaluation Conference (LREC). [paper] [bib]

• The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration
  Arya D. McCarthy, Rachel Wicks, Dylan Lewis, Aaron Mueller, Winston Wu, Oliver Adams, Garrett Nicolai, Matt Post, David Yarowsky. Language Resources and Evaluation Conference (LREC). [paper] [bib]

• Fine-grained Morphosyntactic Analysis and Generation Tools for More Than One Thousand Languages
  Garrett Nicolai, Dylan Lewis, Arya D. McCarthy, Aaron Mueller, Winston Wu, David Yarowsky. Language Resources and Evaluation Conference (LREC). [paper] [bib]

2019

• Quantity Doesn't Buy Quality Syntax with Neural Language Models
  Marten van Schijndel, Aaron Mueller, Tal Linzen. Empirical Methods in Natural Language Processing & International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). [paper] [poster] [bib]

• Modeling Color Terminology Across Thousands of Languages
  Arya D. McCarthy, Winston Wu, Aaron Mueller, Bill Watson, David Yarowsky. Empirical Methods in Natural Language Processing & International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). [paper] [bib]

• Sentence-Level Adaptation for Low-Resource Neural Machine Translation
  Aaron Mueller*, Yash Kumar Lal*. Workshop on Technologies for MT of Low Resource Languages (LoResMT), at Machine Translation Summit (MTSummit). [paper] [bib]