57 citations · 165 across the 17 of their papers we have counts for
18 papers
Algorithmic Audit of Personalisation Drift in Polarising Topics on TikTok
Branislav Pecher, Adrian Bindas, Jan Jakubcik +8
Social media platforms have become an integral part of everyday life, serving as a primary source of news and information for many users. These platforms increasingly rely on perso…
Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
Branislav Pecher, Michal Spiegel, Robert Belanec +1
Large language models (LLMs) are widely used as zero-shot and few-shot classifiers, where task behaviour is largely controlled through prompting. A growing number of works have obs…
Beyond the Checkbox: Strengthening DSA Compliance Through Social Media Algorithmic Auditing
Sara Solarova, Matúš Mesarčík, Branislav Pecher +1
Algorithms of online platforms are required under the Digital Services Act (DSA) to comply with specific obligations concerning algorithmic transparency, user protection and privac…
Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
Branislav Pecher, Jan Cegin, Robert Belanec +3
Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them promising tools in both high- and low-resource languages. One particularly valuable…
PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
Robert Belanec, Branislav Pecher, Ivan Srba +1
Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limi…
RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
Jan Cegin, Branislav Pecher, Ivan Srba +1
LLMs are powerful generators of synthetic data, which are used for training smaller, specific models. This is especially valuable for low-resource languages, where human-labelled d…
Revisiting Algorithmic Audits of TikTok: Poor Reproducibility and Short-term Validity of Findings
Matej Mosnar, Adam Skurla, Branislav Pecher +5
Social media platforms are constantly shifting towards algorithmically curated content based on implicit or explicit user feedback. Regulators, as well as researchers, are calling…
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
Jan Cegin, Branislav Pecher, Jakub Simko +3
The generative large language models (LLMs) are increasingly used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for classifier f…
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
Branislav Pecher, Jan Cegin, Robert Belanec +3
While fine-tuning of pre-trained language models generally helps to overcome the lack of labelled training samples, it also displays model performance instability. This instability…
Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance
Branislav Pecher, Ivan Srba, Maria Bielikova
When solving NLP tasks with limited labelled data, researchers typically either use a general large language model without further update, or use a small number of labelled samples…
On Sensitivity of Learning with Limited Labelled Data to the Effects of Randomness: Impact of Interactions and Systematic Choices
Branislav Pecher, Ivan Srba, Maria Bielikova
While learning with limited labelled data can improve performance when the labels are lacking, it is also sensitive to the effects of uncontrolled randomness introduced by so-calle…
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
Branislav Pecher, Ivan Srba, Maria Bielikova +1
In few-shot learning, the selection of samples has a significant impact on the performance of the model. While effective sample selection strategies are well-established in supervi…
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
Jan Cegin, Branislav Pecher, Jakub Simko +3
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…
A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness
Branislav Pecher, Ivan Srba, Maria Bielikova
Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning or few-shot learning, aims to effectively train a model using only a small a…
KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
Timo Hromadka, Timotej Smolen, Tomas Remis +2
This paper presents the best-performing solution to the SemEval 2023 Task 3 on the subtask 3 dedicated to persuasion techniques detection. Due to a high multilingual character of t…
Auditing YouTube's Recommendation Algorithm for Misinformation Filter Bubbles
Ivan Srba, Robert Moro, Matus Tomlein +8
In this paper, we present results of an auditing study performed over YouTube aimed at investigating how fast a user can get into a misinformation filter bubble, but also what it t…
Monant Medical Misinformation Dataset: Mapping Articles to Fact-Checked Claims
Ivan Srba, Branislav Pecher, Matus Tomlein +4
False information has a significant negative influence on individuals as well as on the whole society. Especially in the current COVID-19 era, we witness an unprecedented growth of…
An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes
Matus Tomlein, Branislav Pecher, Jakub Simko +7
The negative effects of misinformation filter bubbles in adaptive systems have been known to researchers for some time. Several studies investigated, most prominently on YouTube, h…