用大模型和标签分布学习，预测不同标注者观点并提升效果
DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
- 通过上下文学习模拟标注者视角，生成个性化预测
- 软标签聚合后性能接近甚至超过传统方法
- 为观点多样性研究提供新思路，适合关注标注差异的团队
本文介绍DeMeVa团队在第三届学习分歧共享任务（LeWiDi 2025；Leonardelli等，2025）中的方法。我们探索两个方向：一是使用大语言模型进行上下文学习（ICL），比较不同示例采样策略；二是基于RoBERTa的标签分布学习（LDL）方法，评估多种微调策略。主要贡献有两点：（1）证明ICL能有效预测标注者特定的注释（观点化标注），并将这些预测聚合为软标签，获得具有竞争力的性能；（2）认为LDL方法在软标签预测中前景广阔，值得观点化研究社区进一步探索。
原文摘要 · Abstract (English)
This system paper presents the DeMeVa team's approaches to the third edition of the Learning with Disagreements shared task (LeWiDi 2025; Leonardelli et al., 2025). We explore two directions: in-context learning (ICL) with large language models, where we compare example sampling strategies; and label distribution learning (LDL) methods with RoBERTa (Liu et al., 2019b), where we evaluate several fine-tuning methods. Our contributions are twofold: (1) we show that ICL can effectively predict annotator-specific annotations (perspectivist annotations), and that aggregating these predictions into soft labels yields competitive performance; and (2) we argue that LDL methods are promising for soft label predictions and merit further exploration by the perspectivist community.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。