Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence embeddings into a prototype tree and rank documents via coarse-to-fine traversal. Internal nodes act as concept prototypes, providing multi-granular relevance signals and a transparent rationale through retrieval paths. We instantiate two inference approaches: a generalized best-first search and a lightweight path-sum ranker. We evaluate our approaches on MS MARCO and QQP with encoder (e.g., BERT/T5) and decoder (GPT-2) representations. Our results show that our retrieval approaches match the dot product search on strong encoder embeddings while remaining robust when kNN degrades: with GPT-2 vectors, dot product performance collapses whereas our approaches still retrieve relevant results. Overall, our experiments suggest that Cobweb provides competitive effectiveness, improved robustness to embedding quality, scalability, and interpretable retrieval via hierarchical prototypes.

翻译：神经文档检索通常将语料库视为单一粒度下评分的扁平向量云，导致语料结构利用不足且解释不透明。我们采用Cobweb——一个具备层次感知能力的框架——将句子嵌入组织成原型树，并通过从粗到细的遍历对文档进行排序。内部节点充当概念原型，通过检索路径提供多粒度相关性信号和透明的推理依据。我们实现了两种推理方法：广义最佳优先搜索和轻量级路径求和排序器。我们在MS MARCO和QQP数据集上使用编码器（如BERT/T5）和解码器（GPT-2）表示进行评估。实验结果表明，我们的检索方法在强编码器嵌入上可与点积搜索相媲美，同时在kNN性能下降时保持稳健性：使用GPT-2向量时，点积方法性能崩溃，而我们的方法仍能检索到相关结果。总体而言，实验表明Cobweb通过分层原型提供了具有竞争力的检索效能、对嵌入质量的更强鲁棒性、可扩展性以及可解释的检索过程。