TRAILS
TRAILS
Home
News
People
Publications
Contact
Light
Dark
Automatic
Paper-Conference
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
PDF
Cite
URL
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
PDF
Cite
URL
The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs
Autoregressive large language models (LLMs) exhibit impressive performance across various tasks but struggle with simple arithmetic, …
Tanja Bäumel
,
Josef van Genabith
,
Simon Ostermann
PDF
Cite
URL
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
PDF
Cite
URL
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
PDF
Cite
URL
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
PDF
Cite
URL
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
PDF
Cite
URL
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
PDF
Cite
Code
URL
Automatic Fact-checking in English and Telugu
False information poses a significant global challenge, and manually verifying claims is a time-consuming and resource-intensive …
Ravi Kiran Chikkala
,
Tatiana Anikina
,
Natalia Skachkova
,
Ivan Vykopal
,
Rodrigo Agerri
,
Josef van Genabith
PDF
Cite
URL
Roman Urdu as a Low-Resource Language: Building the First IR Dataset and Baseline
The field of Information Retrieval (IR) increasingly recognizes the importance of inclusivity, yet addressing the needs of low-resource …
Umer Butt
,
Günther Neumann
,
Josef van Genabith
PDF
Cite
URL
«
»
Cite
×