arXiv cs.CL· Samuel Harvan, Jaroslav Kop\v{c}an, Marek \v{S}uppa, Andrej Findor·· 11 小时前AI 评分18
The Brittle Compass：斯洛伐克移民媒体话语中 LLM 提示词敏感性研究
The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse
AI 导读
一项针对斯洛伐克语移民媒体话语的案例研究考察了主题相关性、地理相关性分类与移民来源/目的地地点词提取任务，发现斯洛伐克语母语提示词仅带来随任务而异的有限提升。大模型对提示词变化的鲁棒性显著强于小模型，且指令（系统或任务）是最关键的提示词组成部分，重要性超过示例部分。
正文 · 原文
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.
| Comments: | 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 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01219 [cs.CL] |
| (or arXiv:2611.01219v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01219 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the First Workshop on Advancing NLP for Low-Resource Languages, INCOMA Ltd., 2025, pages 88-101 |
| Related DOI: | https://doi.org/10.26615/978-954-452-100-4-010
DOI(s) linking to related resources |
Submission history
From: Jaroslav Kopčan [view email]
[v1]
Sat, 31 Oct 2026 19:41:05 UTC (447 KB)
来源：arXiv cs.CL · arxiv.org