TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

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 $\text{textsc}TaSR-RAG$, 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, $\text{textsc}TaSR-RAG$ 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, $\text{textsc}TaSR-RAG$ resolves intermediate variables and reduces entity conflation without explicit graph construction or exhaustive search. Experiments on multiple multi-hop question answering benchmarks show that $\text{textsc}TaSR-RAG$ consistently outperforms strong RAG and structured-RAG baselines by up to 14%, while producing clearer evidence attribution and more faithful reasoning traces.