❀ LiLaC Lab ❀
This is the homepage of the Learning in Language and Computation (LiLaC) lab at the Khoury College of Computer Sciences, Northeastern University. We study how language models learn and represent language, with a focus on multilingual NLP and the intersection of NLP and computational linguistics. Our goal is to use analysis insights to build NLP systems that work better and more equitably across the world's languages.
Lab Members
 Asst. Professor |
 Ph.D. Student |
 Ph.D. Student |
 Ph.D. Student |
 Ph.D. Student (TU Wien) |
Recent Papers
Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models
Varvara Arzt, Allan Hanbury, and Terra Blevins. Preprint, 2026.
[paper]
Varvara Arzt, Allan Hanbury, and Terra Blevins. Preprint, 2026.
[paper]
Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
Sanchit Ahuja and Terra Blevins. Preprint, 2026.
[paper]
Sanchit Ahuja and Terra Blevins. Preprint, 2026.
[paper]
Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
Terra Blevins. Preprint, 2026.
[paper]
Terra Blevins. Preprint, 2026.
[paper]
Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark
Terra Blevins, Stephen Mayhew, Marek Suppa, Hila Gonen, Shachar Mirkin, Vasile Pais, Kaja Dobrovoljc, Voula Giouli, Jun Kevin, Enes Yılandiloğlu, Eugene Jang, Eungseo Kim, Jeongyeon Seo, Xenophon Gialis, and Yuval Pinter. To Appear in the 2026 International Conference on Language Resources and Evaluation (LREC), 2026.
[paper]
Terra Blevins, Stephen Mayhew, Marek Suppa, Hila Gonen, Shachar Mirkin, Vasile Pais, Kaja Dobrovoljc, Voula Giouli, Jun Kevin, Enes Yılandiloğlu, Eugene Jang, Eungseo Kim, Jeongyeon Seo, Xenophon Gialis, and Yuval Pinter. To Appear in the 2026 International Conference on Language Resources and Evaluation (LREC), 2026.
[paper]
Do language models accommodate their users? A study of linguistic convergence
Terra Blevins, Susanne Schmalwieser, and Benjamin Roth.
In The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026.
[paper]
Terra Blevins, Susanne Schmalwieser, and Benjamin Roth.
In The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026.
[paper]
Joining the LiLaC Lab
The main research themes in the LiLaC Lab are multilingual NLP, linguistic analysis of AI systems, and computational linguistics. I am looking for students who are broadly interested in these areas of research.
If you are interested in joining my lab:
- • As a Ph.D. student: Thank you for your interest! I will take students through Khoury College's Computer Science Ph.D. program. Please see the admissions page for details on the application process. The best way to make sure I see your application is to list me as a potential advisor and mention me in your Statement of Purpose. Emailing me won't affect admission decisions, and I am not able to respond to individual admissions emails.
- • As an undergraduate or master's student at Northeastern: I will accept student researchers into the lab on a rolling basis based on fit for our current research projects. The best way to work with us is to take CS 4120 or CS 6120 and then reach out. Please note that my lab focuses on multilingual NLP and computational linguistics; please take a look at our recent publications before reaching out to see if these areas are interesting to you!
- • As a remote intern or visiting student: Unfortunately, I won't be able to host visitors or remote interns.