cs.CLOct 31, 2026

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

Authors: Samuel Harvan, Jaroslav Kopčan, Marek Šuppa, Andrej Findor

Organizations: Central European University, Vienna, Austria · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · Cisco Systems · Comenius University in Bratislava, Slovakia

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.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

    Apr 18, 2026Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang +1Multilingual Language Model EvaluationLLM Prompting

  2. sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak

    Oct 6, 2026Marek Šuppa, Ivan Vykopal, Andrej Ridzik +9LLM EvaluationMultilingual Language Model Evaluation

  3. Investigating the Influence of Prompt and Response Languages on LLM Content Generation

    Aug 22, 2026Thi Thanh Nhan Nguyen, Mai Khoi Tieu, Michael A. Riegler +2LLM PromptingMultilingual Language Model Evaluation