Aaron Mueller received his PhD in Computer Science at Johns Hopkins University’s Center for Language & Speech Processing. His research centers on natural language processing (NLP), interpreting the decision-making mechanisms of NLP systems, and evaluating the robustness of neural language models. His work also focuses on improving language models’ abilities across multiple languages. His graduate studies were supported by a National Science Foundation Graduate Research Fellowship.
For his post-doc, Dr. Mueller splits his time between the faculties of Computer Sciences at Technion – Israel Institute of Technology in Haifa and Northeastern University in Boston. His current research focuses on targeted model editing methods; he interprets how language models make decisions, so that we can make targeted fixes to improve their abilities without removing other general information that the model has already learned. Dr. Mueller’s work aims to improve language models’ general reasoning abilities. Language technologies (like machine translation systems, home assistants, or automated chat systems) are increasingly based on language models, so this work could lead to broader improvements in the way humans interact with these technologies.
Outside of his PhD and post-doc, Aaron has also researched efficient NLP during internships at Amazon Web Services and Meta, and has previously conducted research at the University of Massachusetts Amherst and New York University.