PaperScope
LIVE · 2026-11-03 05:40 UTC

The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse

Samuel Harvan, Jaroslav Kopčan, Marek Šuppa, Andrej Findor

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2611.01219 v1
Category
Submitted
2026-10-31

Abstract

In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak) prompts yield a modest, task-dependent gains, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions (system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.

Comment: 14 pages, 16 figures. Published in the Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages (LowResNLP 2025), associated with RANLP 2025, Varna, Bulgaria

Journal: Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages, INCOMA Ltd., 2025, pages 88-101

arXiv abs page · PDF · same-day batch