Paper-Conference

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

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

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

TenseLoC: Tense Localization and Control in a Multilingual LLM

Multilingual language models excel across languages, yet how they internally encode grammatical tense remains largely unclear. We …

Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, David Marecek, Josef van Genabith, Koel Dutta Chowdhury

Saarland-Groningen at NADI 2025 Shared Task: Effective Dialectal Arabic Speech Processing under Data Constraints

We present our systems for the NADI 2025 shared task on multidialectal Arabic speech processing, participating in both spoken dialect …

Badr M. Abdullah, Yusser Al Ghussin, Zena Al-Khalili, Ömer Tarik Özyilmaz, Matias Valdenegro-Toro, Simon Ostermann, Dietrich Klakow

A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, …

Tatiana Anikina, Jan Cegin, Jakub Simko, Simon Ostermann

Building Common Ground in Dialogue: A Survey

Common ground plays a crucial role in human communication since it helps to establish shared knowledge. However, common ground is also …

Tatiana Anikina, Alina Leippert, Simon Ostermann

Large Language Models for Multilingual Previously Fact-Checked Claim Detection

In our era of widespread false information, human fact-checkers often face the challenge of duplicating efforts when verifying claims …

Ivan Vykopal, Matus Pikuliak, Simon Ostermann, Tatiana Anikina, Michal Gregor, Marian Simko

Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems

Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered considerable …

Qianli Wang, Tatiana Anikina, Nils Feldhus, Simon Ostermann, Fedor Splitt, Jiaao Li, Yoana Tsoneva, Sebastian Möller, Vera Schmitt

PolBiX: Detecting LLMs' Political Bias in Fact-Checking through X-phemisms

Large Language Models are increasingly used in applications requiring objective assessment, which could be compromised by political …

Charlott Jakob, David Harbecke, Patrick Parschan, Pia Wenzel Neves, Vera Schmitt

PolBiX: Detecting LLMs' Political Bias in Fact-Checking through X-phemisms