Numerous publications accepted at EMNLP 2026

Numerous scientific publications from our department were accepted at the Empirical Methods in Natural Language Processing (EMNLP) .
Congratulations to all authors!

• „FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing“
  by Yusser Al Ghussin, Eva Gavaller, Cristina España-Bonet, Josef van Genabith, Simon Ostermann
• „When Tokenization is Secretly Output Supervision“ 
  by Tanja Baeumel, Josef van Genabith, Simon Ostermann
• „Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation“ 
  by Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann
• „A Retrieval Conditioned Rebinding Circuit for Dynamic Entity Tracking in Large Language Models“ 
  by Soyoung Oh, Vera Demberg
• „Accelerating Constrained Decoding with Token Space Compression“ 
  by Michael Sullivan, Alexander Koller
• „AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing“ 
  by Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan, Alexander Koller
• „Tracing Stereotypes from Representation to Output in Multilingual LLMs“ 
  by Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen, Josef van Genabith, Koel Dutta Chowdhury

EMNLP Findings:

• „Formatting Confounds in AI Text Detection: A Clever Hans Effect“ 
  by Koel Dutta Chowdhury, Cristina España-Bonet, Josef van Genabith
• „TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment“ 
  by Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele
• „Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs“ 
  by Mikhail Sonkin, Tanja Baeumel, Daniil Gurgurov, Josef van Genabith, Simon Ostermann
• „Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations“ 
  by Qianli Wang, Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian Möller, Vera Schmitt
• „Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization“
  by Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann