ExpertLens：可视化嵌入空间实现MoE增强检索器的后置可解释性
原标题：ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers
AI 摘要
arXiv 论文提出 ExpertLens，一个针对 MoE 增强型稠密检索器的后置可解释性框架，利用判别式嵌入空间可视化和概念激活向量，揭示专家路由如何影响嵌入空间结构和检索效果。实验在五个 IR 基准和两个稠密检索器上进行，结果表明专家路由能改善嵌入空间几何结构，且存在通用专家和具有语言特化的少数专家。该框架补充了现有特征级归因方法，推动神经 IR 的全局可解释性。
正文节选
ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers Abstract. Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Despite their effectiveness, these models operate as black boxes, limiting the interpretability of their ranking decisions. Existing post-hoc explainability methods for neural rankers primarily focus on feature-level attributions, which can be insu