arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.20168cs.CL
收藏

德鲁特在SemEval-2026任务6:DeBERTa与LLM增强数据用于揭示政治问题回避

Duluth at SemEval-2026 Task 6: DeBERTa with LLM-Augmented Data for Unmasking Political Question Evasions

Department of Computer Science(计算机科学系);University of Minnesota Duluth(明尼苏达大学杜鲁斯)

Shujauddin Syed, Ted Pedersen

AI总结:

本文提出德鲁特在SemEval-2026任务6上的方法,使用DeBERTa-V3-base结合焦点损失和布尔话语特征,通过LLM增强数据提升政治问题回避识别的宏F1值达0.76。

摘要:

本文介绍了德鲁特在SemEval-2026任务6上的方法,针对CLARITY任务:揭示政治问题回避。我们处理任务1(清晰度分级分类)和任务2(回避分级分类),均需对美国总统采访中的问答对进行分类,使用两级响应清晰度分类法。我们的系统基于DeBERTa-V3-base,扩展了焦点损失、分层学习率衰减和布尔话语特征。为解决训练数据中的类别不平衡问题,我们使用Gemini 3和Claude Sonnet 4.5生成合成示例来增强少数类。我们的最佳配置在任务1评估集上实现了宏F1值0.76,排名第8名(共40支队伍)。排名第一的系统(TeleAI)达到了0.89,而所有参与者的平均分数为0.70。错误分析显示,主要的分类错误源是Ambivalent与Clear Reply响应的混淆,这种模式反映了人类标注者的分歧。我们的发现表明,基于LLM的数据增强可以有意义地提高细微政治话语任务中少数类召回率。

英文摘要:

This paper presents the Duluth approach to SemEval-2026 Task 6 on CLARITY: Unmasking Political Question Evasions. We address Task 1 (clarity-level classification) and Task 2 (evasion-level classification), both of which involve classifying question--answer pairs from U.S.\ presidential interviews using a two-level taxonomy of response clarity. Our system is based on DeBERTa-V3-base, extended with focal loss, layer-wise learning rate decay, and boolean discourse features. To address class imbalance in the training data, we augment minority classes using synthetic examples generated by Gemini 3 and Claude Sonnet 4.5. Our best configuration achieved a Macro F1 of 0.76 on the Task 1 evaluation set, placing 8th out of 40 teams. The top-ranked system (TeleAI) achieved 0.89, while the mean score across participants was 0.70. Error analysis reveals that the dominant source of misclassification is confusion between Ambivalent and Clear Reply responses, a pattern that mirrors disagreements among human annotators. Our findings demonstrate that LLM-based data augmentation can meaningfully improve minority-class recall on nuanced political discourse tasks.

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。

↑