Research

Paper

AI LLM March 10, 2026

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

Authors

Jiashuo Sun, Yixuan Xie, Jimeng Shi, Shaowen Wang, Jiawei Han

Abstract

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.

Metadata

arXiv ID: 2603.09341
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09341v1</id>\n    <title>TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation</title>\n    <updated>2026-03-10T08:16:36Z</updated>\n    <link href='https://arxiv.org/abs/2603.09341v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09341v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.\n  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.\n  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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-10T08:16:36Z</published>\n    <arxiv:comment>14 pages, 7 tables, 5 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Jiashuo Sun</name>\n    </author>\n    <author>\n      <name>Yixuan Xie</name>\n    </author>\n    <author>\n      <name>Jimeng Shi</name>\n    </author>\n    <author>\n      <name>Shaowen Wang</name>\n    </author>\n    <author>\n      <name>Jiawei Han</name>\n    </author>\n  </entry>"
}