Zahlreiche Beiträge beim ACL 2026 angenommen

Zahlreiche wissenschaftliche Beiträge unserer Fachrichtung wurden bei der Association for Computational Linguistics (ACL) 2026 angenommen. Herzlichen Glückwunsch an alle Autorinnen und Autoren!

Main conference:

• “Disco-RAG: Discourse-Aware Retrieval-Augmented Generation” 
  von Dongqi Liu, Hang Ding, Qiming Feng, Jian Li, Xurong Xie, Zhucun Xue, Chengjie Wang, Jiangning Zhang, Yabiao Wang.
• "From Weights to Activations: Is Steering the Next Frontier of Adaptation?"
  von Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael A. Hedderich, Sebastian Lapuschkin, Wojciech Samek, Vera Schmitt.
• "Systematicity between Forms and Meanings across Languages Supports Efficient Communication"
  von Doreen Osmelak, Yang Xu, Michael Hahn, Kate McCurdy.
• “Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models”
  von Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin, Josef van Genabith, Deyi Xiong.

Findings:

• “CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark”
  von Daniil Gurgurov , Yusser Al Ghussin, Tanja Baeumel, Cheng-Ting Chou, Patrick Schramowski, Marius Mosbach, Josef van Genabith, Simon Ostermann.
• “DualFact+: A Multimodal Fact Verification Framework for Procedural Video Captioning”
  von Cennet Oguz, Yasser Hamidullah, Josef van Genabith, Simon Ostermann.
• “System-Mediated Attention Imbalances Make Vision-Language Models Say Yes”
  von Tsan Tsai Chan, Varsha Suresh, Anisha Saha, Michael Hahn, Vera Demberg.