Scientific Contribuions accepted at COLM 2025

We are happy to announce that contributions by members of our department have been accepted at the Conference on Language Modeling (COLM) 2025.
Congratulations to all authors!

• “Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B” by Aleksandra Bakalova, Yana Veitsman, Xinting Huang and Michael Hahn.
• “A Meta-Evaluation of Measuring LLM Misgendering” by Arjun Subramonian, Vagrant Gautam, Preethi Seshadri, Dietrich Klakow, Kai-Wei Chang and Yizhou Sun.
• "How Relative Input Length affects Positional Biases in LLMs" by Blerta Veseli, Julian Chibane, Mariya Toneva and Alexander Koller.