Six publications accepted at IJCNLP-AACL 2025

Six research papers from our department have been accepted for presentation at the International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025).
Congratulations to all authors!

Main conference:

• “Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation”
  by Daniil Gurgurov, Katharina Trinley, Yusser Al Ghussin, Tanja Baeumel, Josef van Genabith, Simon Ostermann
• “ProofTeller: What LLMs struggle with while reasoning with Formal Proofs”
  by Mayank Jobanputra, Alisa Kovtunova, Brisca Balthes, Fedor Grigoryevich Pogulskiy, Yifan Wang, Stefan Borgwardt, Vera Demberg  

Findings:

• “Surprisal Dynamics for the Detection of Multi-Word Expressions in English”
  by Diego Alves, Sergei Bagdasarov, Elke Teich
• “Modular Arithmetic: Language Models Solve Math Digit by Digit”
  by Tanja Baeumel, Daniil Gurgurov, Yusser al Ghussin, Josef van Genabith, Simon Ostermann
• “Multilingual Political Views of Large Language Models: Identification and Steering”
  by Daniil Gurgurov, Katharina Trinley, Ivan Vykopal, Josef van Genabith, Simon Ostermann, Roberto Zamparelli (Findings)
• “Cross-Prompt Encoder for Low-Performing Languages”
  by Beso Mikaberidze, Teimuraz Saghinadze, Simon Ostermann, Philipp Muller