让生成式检索可解释，通过分步生成类别路径来说明为何选某文档。
Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths
- 先生成从宽泛到具体的类别路径，再输出文档ID，实现可解释性。
- 在多个数据集上提升检索性能，最高达12.3%的Recall提升。
- 适合需要透明决策过程的场景，如医疗、金融领域检索。
生成式检索直接解码文档标识符（docid）作为查询的回答，无法回答“为何检索该文档”这类问题。为解决此局限，我们提出层次化类别路径增强的生成式检索（HyPE），通过逐步生成从宽泛到具体的语义类别路径，再解码docid，提供详细决策解释。训练时，利用外部高质量语义层次结构构建类别路径，借助大模型为每篇文档筛选合适候选路径，并用路径增强的数据集优化生成式检索模型。推理时，采用路径感知排序策略聚合多样主题信息，使最相关文档在最终排序列表中优先呈现。大量实验表明，HyPE不仅显著提升可解释性，还提高了检索性能。
原文摘要 · Abstract (English)
Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for ``why is this document retrieved?''. To address this limitation, we propose Hierarchical Category Path-Enhanced Generative Retrieval (HyPE), which enhances explainability by first generating hierarchical category paths step-by-step then decoding docid. By leveraging hierarchical category paths which progress from broader to more specific semantic categories, HyPE can provide detailed explanation for its retrieval decision. For training, HyPE constructs category paths with external high-quality semantic hierarchy, leverages LLM to select appropriate candidate paths for each document, and optimizes the generative retrieval model with path-augmented dataset. During inference, HyPE utilizes path-aware ranking strategy to aggregate diverse topic information, allowing the most relevant documents to be prioritized in the final ranked list of docids. Our extensive experiments demonstrate that HyPE not only offers a high level of explainability but also improves the retrieval performance.
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。