8 citations · 14 across the 20 of their papers we have counts for
10 papers · 1 filter
Compositional Multilingual and Behavioral Attribute Steering
Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel +2
This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language, jailbreak, and conciseness, we inve…
Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs
Mikhail Sonkin, Tanja Baeumel, Daniil Gurgurov +2
Multilingual large language models (mLLMs) achieve strong performance in machine translation, yet our understanding of the mechanisms by which they transform representations from o…
A Sovereign, Open-Source Foundation Model for German and English
Soofi-Team, :, Benedikt Droste +30
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B…
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin +1
Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task per…
DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
Yusser Al Ghussin, Daniil Gurgurov, Yasser Hamidullah +3
Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge remains uneven across regions and languages. We pre…
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…
The Latin Substrate: How Language Models Represent and Mediate Script Choice
Daniil Gurgurov, Alan Saji, Katharina Trinley +2
Many languages are written in multiple scripts, requiring large language models (LLMs) to generate equivalent linguistic content in distinct orthographic forms. While prior work su…
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…
ReasonXL: A Large-Scale Corpus for Language-Specific Reasoning in LLMs
Daniil Gurgurov, Tom Röhr, Sebastian von Rohrscheidt +3
Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in the reasoning traces they produce: even…
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…