SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

ACL ARR 2025 May Submission6656 Authors

Abstract: Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "What is the distribution of IEEE Fellows among various fields of study?", which requires retrieving information from diverse sources like Wikipedia pages. The effectiveness of current retrieval-augmented generation (RAG) methods is limited by the LLMs' capacity to aggregate insights from numerous pages. To address this gap, this paper introduces a structured RAG (SRAG) framework that systematically organizes extracted entities into relational tables ((e.g., tabulating entities with schema columns like "name" and "field of study") and then applies table-based reasoning techniques to get precise answer. Our approach decouples retrieval and reasoning, enabling LLMs to focus on structured data analysis rather than raw text aggregation. Extensive experiments on Wikipedia-based multi-entity QA tasks demonstrate that SRAG significantly outperforms state-of-the-art long-context LLMs and RAG solutions, achieving a 29.6% improvement in accuracy. The results underscore the efficacy of structuring unstructured data to enhance LLMs’ reasoning capabilities. The source code and data have been made available at https://github.com/tl2309/SRAG.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: knowledge base QA, open information extraction, retrieval-augmented generation

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English

Submission Number: 6656