arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.03334cs.CLcs.LG
收藏

Lingo_Research_Group 在 SemEval-2026 任务 9:评估用于极化检测的提示变体

Lingo_Research_Group at SemEval-2026 Task 9: Evaluating Prompt Variants for Polarization Detection

Lingo Research Group(Lingo研究组);Indian Institute of Technology Gandhinagar(印度理工学院加尔各答分校);Noida Institute of Engineering and Technology(诺伊达工程与技术学院);ML Collective(ML集体)

Pritam Kadasi, Anuj Tiwari, Mayank Singh

AI总结:

本文针对 SemEval-2026 任务 9 的多语言极化检测,通过设计 12 种不同提示变体,使用 aya-101 和 Gemma3-27B 模型,在三个子任务上评估提示方法的效果,发现提示方法在粗粒度极化检测上有效,但在细粒度多标签分类上困难增加。

摘要:

本文提交的成果针对 SemEval-2026 任务 9:多语言文本分类挑战——极化检测,涵盖了所有三个子任务:(1) 二元极化检测,(2) 极化类型分类,以及 (3) 极化表现识别。我们采用系统性的短设计提示研究方法,考虑了 12 种在术语清晰度、定义详细程度、推理指导以及上下文示例使用上不同的设计提示。实验使用 aya-101 和 Gemma3-27B 进行,后者因性能考虑在开发阶段结束时被选用于提交。我们的系统在官方测试集上(22 种语言的平均值)在子任务 1 上的平均宏 F1 得分为 0.762,子任务 2 为 0.587,子任务 3 为 0.444,平均准确率分别为 0.819、0.678 和 0.498。通过跨任务和跨语言分析,我们证明基于提示的方法可以有效检测粗粒度极化,但在细粒度多标签社会语言学分类方面遇到越来越多的困难。

英文摘要:

Our submission presented in this paper is for SemEval-2026 Task 9: Multilingual Text Classification Challenge - Polarization Detection and it covers all three subtasks: (1) binary polarization detection, (2) polarization type classification and (3) polarization manifestation identification. We adopt a systematic approach of research on short designed prompts by considering twelve designed prompts that are different in terminology clarity, detail of the definition, guidance of reasoning and in-context examples use. The experiments are conducted using aya-101 and Gemma3-27B, with the latter chosen for the submission at the end of the development through performance considerations. Our system has an average macro level F1-score of 0.762 on Subtask 1, 0.587 on Subtask 2 and 0.444 on Subtask 3 with the average accuracy of 0.819, 0.678 and 0.498, respectively, on the official test set averaged among 22 languages, respectively. With cross-task and cross-lingual analysis, we demonstrate that prompt-based approaches can be used effectively to detect coarse grained polarization but encounter more and more difficulties as far as fine-grained and multi-label sociolinguistic classification is concerned.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑