The papers span mechanistic interpretability, multilingual and low-resource NLP, tokenization, and explainability, reflecting the range of work happening across the lab. Congratulations to all authors!
Main Conference:
Tracing Stereotypes from Representation to Output in Multilingual LLMs
Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen, Josef van Genabith, Koel Dutta Chowdhury
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann
FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing
Yusser Al Ghussin, Eva Gavaller, Cristina España-Bonet, Josef van Genabith, Simon Ostermann
When Tokenization is Secretly Output Supervision
Tanja Baeumel, Josef van Genabith, Simon Ostermann
Findings:
Formatting Confounds in AI Text Detection: A Clever Hans Effect
Koel Dutta Chowdhury, Cristina España-Bonet, Josef van Genabith
Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
Qianli Wang, Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian Möller, Vera Schmitt
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann
Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
Mikhail Sonkin, Tanja Baeumel, Daniil Gurgurov, Josef van Genabith, Simon Ostermann