no code implementations • 20 Feb 2024 • Branislav Pecher, Ivan Srba, Maria Bielikova
When performance variance is taken into consideration, the number of required labels increases on average by $100 - 200\%$ and even up to $1500\%$ in specific cases.
no code implementations • 20 Feb 2024 • Branislav Pecher, Ivan Srba, Maria Bielikova
To measure the true effects of an individual randomness factor, our method mitigates the effects of other factors and observes how the performance varies across multiple runs.
no code implementations • 5 Feb 2024 • Branislav Pecher, Ivan Srba, Maria Bielikova, Joaquin Vanschoren
In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the limited number of samples used to train a model have a significant impact on the overall success.
no code implementations • 15 Jan 2024 • Dominik Macko, Robert Moro, Adaku Uchendu, Ivan Srba, Jason Samuel Lucas, Michiharu Yamashita, Nafis Irtiza Tripto, Dongwon Lee, Jakub Simko, Maria Bielikova
However, it is susceptible to authorship obfuscation (AO) methods, such as paraphrasing, which can cause MGTs to evade detection.
1 code implementation • 12 Jan 2024 • Jan Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Maria Bielikova, Peter Brusilovsky
The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune downstream models.
no code implementations • 2 Dec 2023 • Branislav Pecher, Ivan Srba, Maria Bielikova
Recently, this area started to attract a research attention and the number of relevant studies is continuously growing.
1 code implementation • 15 Nov 2023 • Ivan Vykopal, Matúš Pikuliak, Ivan Srba, Robert Moro, Dominik Macko, Maria Bielikova
Automated disinformation generation is often listed as an important risk associated with large language models (LLMs).
no code implementations • 14 Nov 2023 • Nafis Irtiza Tripto, Saranya Venkatraman, Dominik Macko, Robert Moro, Ivan Srba, Adaku Uchendu, Thai Le, Dongwon Lee
In the realm of text manipulation and linguistic transformation, the question of authorship has always been a subject of fascination and philosophical inquiry.
no code implementations • 10 Nov 2023 • Martin Hyben, Sebastian Kula, Ivan Srba, Robert Moro, Jakub Simko
This study compares the performance of (1) fine-tuned models and (2) extremely large language models on the task of check-worthy claim detection.
1 code implementation • 20 Oct 2023 • Dominik Macko, Robert Moro, Adaku Uchendu, Jason Samuel Lucas, Michiharu Yamashita, Matúš Pikuliak, Ivan Srba, Thai Le, Dongwon Lee, Jakub Simko, Maria Bielikova
There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings.
1 code implementation • 14 Aug 2023 • Olesya Razuvayevskaya, Ben Wu, Joao A. Leite, Freddy Heppell, Ivan Srba, Carolina Scarton, Kalina Bontcheva, Xingyi Song
Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuning techniques designed to make the training of language models more efficient.
1 code implementation • 13 May 2023 • Matúš Pikuliak, Ivan Srba, Robert Moro, Timo Hromadka, Timotej Smolen, Martin Melisek, Ivan Vykopal, Jakub Simko, Juraj Podrouzek, Maria Bielikova
Fact-checkers are often hampered by the sheer amount of online content that needs to be fact-checked.
1 code implementation • 24 Apr 2023 • Timo Hromadka, Timotej Smolen, Tomas Remis, Branislav Pecher, Ivan Srba
This paper presents the best-performing solution to the SemEval 2023 Task 3 on the subtask 3 dedicated to persuasion techniques detection.
no code implementations • 22 Nov 2022 • Andrea Hrckova, Robert Moro, Ivan Srba, Jakub Simko, Maria Bielikova
Second, we have identified fact-checkers' needs and pains focusing on so far unexplored dimensions and emphasizing the needs of fact-checkers from Central and Eastern Europe as well as from low-resource language groups which have implications for development of new resources (datasets) as well as for the focus of AI research in this domain.
1 code implementation • 18 Oct 2022 • Ivan Srba, Robert Moro, Matus Tomlein, Branislav Pecher, Jakub Simko, Elena Stefancova, Michal Kompan, Andrea Hrckova, Juraj Podrouzek, Adrian Gavornik, Maria Bielikova
We also observe a sudden decrease of misinformation filter bubble effect when misinformation debunking videos are watched after misinformation promoting videos, suggesting a strong contextuality of recommendations.
1 code implementation • 26 Apr 2022 • Ivan Srba, Branislav Pecher, Matus Tomlein, Robert Moro, Elena Stefancova, Jakub Simko, Maria Bielikova
It also contains 573 manually and more than 51k automatically labelled mappings between claims and articles.
1 code implementation • 25 Mar 2022 • Matus Tomlein, Branislav Pecher, Jakub Simko, Ivan Srba, Robert Moro, Elena Stefancova, Michal Kompan, Andrea Hrckova, Juraj Podrouzek, Maria Bielikova
We present a study in which pre-programmed agents (acting as YouTube users) delve into misinformation filter bubbles by watching misinformation promoting content (for various topics).