发表机构
Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出GCUL框架，利用聚类引导学习识别文本情感分类中的歧义样本，通过几何结构提升选择性分类性能，显著提高准确率并有效预判失败场景。
AI 中文摘要
选择性分类使模型能够对不确定的实例弃权（不执行）预测，但现有方法通常通过置信度分数、预定义的覆盖率约束或实例级距离度量来拒绝这些实例。这些方法可能忽略学习表示空间中困难样本的集体几何结构。我们提出了基于引导聚类的非确定性学习（GCUL），一种几何引导的选择性分类框架，将误分类和歧义实例识别为表示空间中潜在的混淆吸引子。GCUL采用三阶段程序来初始化、聚类并显式重新标记这一不确定区域，使拒绝边界从底层表示几何中产生，而非来自预设的拒绝率。我们进一步推导了一个选择性分数和一个几何充分条件，该条件刻画了拒绝何时能提供正向操作效用，从而支持部署前的可行性评估。GCUL将DistilBERT的准确率从89.37%提升至94.98%，且拒绝率低于9%。除准确率外，我们的选择性分数正确预检测了所有基线均失败的唯一数据集（GoEmotion），受控模拟产生6.1%的I型错误和0%的II型错误，验证了充分条件的保守性。这些结果表明，集体表示几何为选择性预测提供了一种有用的替代视角。
英文摘要
Selective classification enables a model to abstain from predictions on uncertain instances, but existing approaches typically reject them through confidence scores, predefined coverage constraints or instance-level distance measures. These approaches may overlook the collective geometric structure of difficult samples in learned representation spaces. We propose Guided Clustering-based Uncertain Learning (GCUL), a geometric-guided selective classification framework that identifies misclassified and ambiguous instances as a potential confusion attractor in the representation space. GCUL uses a three-phase procedure to initialize, cluster, and explicitly relabel this uncertain region, allowing the rejection boundary to emerge from the underlying representation geometry rather than from a prescribed rejection rate. We further derive a selectivity score and a geometric sufficient condition that characterizes when rejection can provide positive operational utility, enabling pre-deployment feasibility assessment. GCUL improves DistilBERT accuracy from 89.37 percent to 94.98 percent with less than 9 percent rejection. Beyond accuracy, our selectivity score correctly pre-detects the only dataset (GoEmotion) where all baselines fail, and controlled simulations yield 6.1 percent Type-I and 0 percent Type-II errors, validating the sufficient condition's conservatism. These results suggest that collective representation geometry provides a useful alternative perspective for selective prediction.
Comments15 pages, 8 figures, 21 tables
