TaSR-RAG：基于分类的结构化推理用于检索增强生成
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
AI总结：
TaSR-RAG通过基于分类的结构化推理框架，提升检索增强生成任务的证据选择精度和推理质量。
摘要：
检索增强生成（RAG）通过将生成过程与外部证据相结合，帮助大型语言模型（LLMs）回答知识密集型和时间敏感型问题。然而，大多数RAG系统仍检索无结构的片段，并依赖单次生成，这通常会产生冗余上下文、信息密度低和脆弱的多跳推理。虽然结构化RAG管道可以提高基础性，但通常需要成本高且容易出错的图构建或施加刚性的实体中心结构，这些结构与查询的推理链不一致。我们提出了TaSR-RAG，一种基于分类的结构化推理框架用于证据选择。我们将查询和文档表示为关系三元组，并使用轻量级的两级分类学来约束实体语义，以平衡通用性和精确性。给定一个复杂问题，TaSR-RAG将其分解为一个有序的三元组子查询序列，带有显式的潜在变量，然后通过混合三元组匹配进行分步证据选择，该匹配结合了对原始三元组的语义相似性和对类型三元组的结构一致性。通过在各步骤间维护一个显式的实体绑定表，TaSR-RAG解决中间变量并减少实体混淆，而无需显式图构建或穷尽搜索。在多个多跳问答基准测试中，实验表明TaSR-RAG在多个多跳问答基准测试中始终优于强大的RAG和结构化RAG基线，高出高达14%，同时产生更清晰的证据归属和更忠实的推理轨迹。
英文摘要：
Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve unstructured chunks and rely on one-shot generation, which often yields redundant context, low information density, and brittle multi-hop reasoning. While structured RAG pipelines can improve grounding, they typically require costly and error-prone graph construction or impose rigid entity-centric structures that do not align with the query's reasoning chain. We propose \textsc{TaSR-RAG}, a taxonomy-guided structured reasoning framework for evidence selection. We represent both queries and documents as relational triples, and constrain entity semantics with a lightweight two-level taxonomy to balance generalization and precision. Given a complex question, \textsc{TaSR-RAG} decomposes it into an ordered sequence of triple sub-queries with explicit latent variables, then performs step-wise evidence selection via hybrid triple matching that combines semantic similarity over raw triples with structural consistency over typed triples. By maintaining an explicit entity binding table across steps, \textsc{TaSR-RAG} resolves intermediate variables and reduces entity conflation without explicit graph construction or exhaustive search. Experiments on multiple multi-hop question answering benchmarks show that \textsc{TaSR-RAG} consistently outperforms strong RAG and structured-RAG baselines by up to 14\%, while producing clearer evidence attribution and more faithful reasoning traces.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
