TRAILS
TRAILS
Home
News
People
Publications
Contact
Light
Dark
Automatic
Paper-Conference
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
Post-training adaptation of large language models is commonly achieved through parameter updates or input based methods such as …
Simon Ostermann
,
Daniil Gurgurov
,
Tanja Bäumel
,
Michael A. Hedderich
,
Sebastian Lapuschkin
,
Wojciech Samek
,
Vera Schmitt
PDF
Cite
URL
Dfki-mlt at semeval-2026 task 7: Steering multilingual models towards cultural knowledge
Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge …
Yusser Al Ghussin
,
Daniil Gurgurov
,
Yasser HAMIDULLAH
,
Josef van Genabith
,
Cristina España-Bonet
,
Simon Ostermann
PDF
Cite
URL
Multilingual steering by design: Multilingual sparse autoencoders and principled layer selection
Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), …
Yusser Al Ghussin
,
Daniil Gurgurov
,
Tanja Bäumel
,
Josef van Genabith
,
Patrick Schramowski
,
Simon Ostermann
PDF
Cite
URL
From Facts to Hypotheses: Joint Detection of Biomedical Relations and Epistemic Commitment Using LLMs
Determining the factual status of biomedical statements, whether affirmed, negated, or uncertain, is essential for accurate …
Aleksandra Gabryszak
,
Phuc Tran Truong
,
Arne Binder
,
Nikola Milosevic
,
Felix-Sebastian Keese
,
Astrid Rheinländer
,
Philippe Thomas
PDF
Cite
Dataset
URL
Poster
Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation
Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision–language models and is …
Yasser HAMIDULLAH
,
Koel Dutta Chowdhury
,
Yusser Al Ghussin
,
Shakib Yazdani
,
Cennet Oguz
,
Josef van Genabith
,
Cristina España-Bonet
PDF
Cite
URL
CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark
Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. …
Daniil Gurgurov
,
Yusser Al Ghussin
,
Tanja Bäumel
,
Cheng-Ting Chou
,
Patrick Schramowski
,
Marius Mosbach
,
Josef van Genabith
,
Simon Ostermann
PDF
Cite
URL
Modular Arithmetic: Language Models Solve Math Digit by Digit
While recent work has begun to uncover the internal strategies that Large Language Models (LLMs) employ for simple arithmetic tasks, a …
Tanja Bäumel
,
Daniil Gurgurov
,
Yusser Al Ghussin
,
Josef van Genabith
,
Simon Ostermann
PDF
Cite
URL
Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
Large language models (LLMs) exhibit strong multilingual abilities, yet the neural mechanisms behind language-specific processing …
Daniil Gurgurov
,
Katharina Trinley
,
Yusser Al Ghussin
,
Tanja Bäumel
,
Josef van Genabith
,
Simon Ostermann
PDF
Cite
URL
Multilingual Political Views of Large Language Models: Identification and Steering
Large language models (LLMs) are increasingly used in everyday tools and applications, raising concerns about their potential influence …
Daniil Gurgurov
,
Katharina Trinley
,
Ivan Vykopal
,
Josef van Genabith
,
Simon Ostermann
,
Roberto Zamparelli
PDF
Cite
URL
On Multilingual Encoder Language Model Compression for Low-Resource Languages
In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely …
Daniil Gurgurov
,
Michal Gregor
,
Josef van Genabith
,
Simon Ostermann
PDF
Cite
URL
»
Cite
×