用分层原型树提升文档检索的可解释性与鲁棒性
Hierarchical Semantic Retrieval with Cobweb
- 构建句子嵌入的层次化原型树，实现粗到细的检索路径
- 在MS MARCO和QQP上表现优于传统方法，尤其在低质量嵌入下仍有效
- 适合需要透明推理过程的场景，如可信AI与可解释搜索
神经文档检索通常将语料库视为单一粒度的向量集合，忽视了结构信息且解释性差。本文提出Cobweb——一种层次感知框架，将句子嵌入组织成原型树，并通过粗到细的遍历进行文档排序。内部节点作为概念原型，提供多粒度相关性信号并生成可解释的检索路径。我们实现了两种推理方法：广义的最优优先搜索与轻量级路径求和排名器。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。结果表明，我们的方法在强编码器嵌入下性能媲美点积搜索，且在kNN退化时仍保持稳健：当GPT-2向量下点积性能崩溃时，我们的方法仍能检索出相关文档。整体实验表明，Cobweb具备竞争力的效果、对嵌入质量的更高鲁棒性、良好的可扩展性以及通过层次原型实现的可解释检索。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。