collaborators

5 papers

cs.CL2026

Judge Circuits

Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia +10

LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its output format changes (e.g.,…

cs.CL2026

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection

Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel +3

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unrelia…

cs.CL2026

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms

Tanja Baeumel, Josef van Genabith, Simon Ostermann

Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain underexplored. To advance the un…

cs.CL2026

From Weights to Activations: Is Steering the Next Frontier of Adaptation?

Simon Ostermann, Daniil Gurgurov, Tanja Baeumel +4

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting…

cs.CL2026

CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark

Daniil Gurgurov, Yusser Al Ghussin, Tanja Baeumel +5

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipula…