8 papers
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin +1
Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task per…
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…
MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models
Martin Hyben, Sebastian Kula, Jan Cegin +3
Large Language Models (LLMs) are beginning to reshape how media professionals verify information, yet automated support for detecting check-worthy claims a key step in the fact-che…
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…
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…
A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages
Tatiana Anikina, Jan Cegin, Jakub Simko +1
Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategie…