6 papers
On Multilingual Encoder Language Model Compression for Low-Resource Languages
Daniil Gurgurov, Michal Gregor, Josef van Genabith +1
In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely compressing multilingual encoder-only language mode…
Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection
Ivan Vykopal, Antonia Karamolegkou, Jaroslav KopÄan +4
Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionat…
Large Language Models for Multilingual Previously Fact-Checked Claim Detection
Ivan Vykopal, Matúš Pikuliak, Simon Ostermann +3
In our era of widespread false information, human fact-checkers often face the challenge of duplicating efforts when verifying claims that may have already been addressed in other…
SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
Qiwei Peng, Robert Moro, Michal Gregor +7
The rapid spread of online disinformation presents a global challenge, and machine learning has been widely explored as a potential solution. However, multilingual settings and low…
A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages
Ivan Vykopal, Martin Hyben, Robert Moro +2
Online disinformation poses a global challenge, placing significant demands on fact-checkers who must verify claims efficiently to prevent the spread of false information. A major…
Overshoot: Taking advantage of future gradients in momentum-based stochastic optimization
Jakub Kopal, Michal Gregor, Santiago de Leon-Martinez +1
Overshoot is a novel, momentum-based stochastic gradient descent optimization method designed to enhance performance beyond standard and Nesterov's momentum. In conventional moment…