5 papers
Strategies for Span Labeling with Large Language Models
Danil Semin, OndÅej DuÅ¡ek, ZdenÄk Kasner
Large language models (LLMs) are increasingly used for text analysis tasks, such as named entity recognition or error detection. Unlike encoder-based models, however, generative ar…
Can LLM Coding Agents Reason About Time Series?
Filip RechtorÃk, OndÅej DuÅ¡ek, ZdenÄk Kasner
Large language models (LLMs) are increasingly being used for automated decision-making systems in finance, healthcare, or environmental monitoring. Time series data are ubiquitous…
LLMs as Span Annotators: A Comparative Study of LLMs and Humans
ZdenÄk Kasner, Vilém Zouhar, PatrÃcia Schmidtová +7
Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score metrics fail to provide actionable feedback. Until recently…
AnimatedLLM: Explaining LLMs with Interactive Visualizations
ZdenÄk Kasner, OndÅej DuÅ¡ek
Large language models (LLMs) are becoming central to natural language processing education, yet materials showing their mechanics are sparse. We present AnimatedLLM, an interactive…
FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation
Kristýna Onderková, OndÅej Plátek, ZdenÄk Kasner +1
Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is…