研究人员开发了一种新的文本道德分类方法，通过对个体标注者观点的建模，而不是依赖于聚合的“地面真实”标签。该方法通过添加一个学习标注者特定特征的层来扩展预训练语言模型，从而改进了对个体标注的预测。研究表明，聚合标签可能会掩盖差异并提供对性能的误导性印象，突出了考虑标注者主观性的好处。 AI
影响 这项研究可能带来更细致、更准确的AI模型，以理解道德价值观等主观内容。
排序理由 该集群描述了一篇关于新颖文本分类方法的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators'…
Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators'…