Feature attribution methods typically provide minimal sufficient evidence justifying a model decision. However, in many applications, such as compliance and cataloging, the full set of contributing features must be identified: complete evidence. We present a case study using existing language models and a medical dataset which contains human-annotated complete evidence. Our findings show that an ensemble approach, aggregating evidence from several models, improves evidence recall over individual models. We examine different ensemble sizes, the effect of evidence-guided training, and provide qualitative insights.

翻译：特征归因方法通常仅提供证明模型决策所需的最小充分证据。然而，在许多应用场景（如合规审查与信息编目）中，必须识别出所有贡献特征：即完整证据。本文通过一项案例研究，利用现有语言模型和包含人工标注完整证据的医学数据集展开分析。研究发现，集成方法通过聚合多个模型的证据，相较于单一模型能够提升证据召回率。我们考察了不同集成规模的影响，探讨了证据引导训练的效果，并提供了定性分析见解。