Structure Guided Retrieval-Augmented Generation for Factual Queries

ACL ARR 2026 January Submission3585 Authors

Keywords: Retrieval-Augmented Generation; Subgraph Matching; Large Language Model

Abstract:

Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect.
However, existing RAG approaches predominantly rely on vector similarity for retrieval, which is prone to semantic noise and fails to ensure that generated responses fully satisfy the complex conditions specified by factual queries, often leading to incorrect answers.
To address this challenge, we introduce a novel research problem, named Exact Retrieval Problem (ERP). To the best of our knowledge, this is the first problem formulation that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions. For this novel problem, we propose Structure Guided Retrieval-Augmented Generation (SG-RAG),
which models the retrieval process as an embedding-based subgraph matching task, and uses the retrieved topological structures to guide the LLM to generate answers that meet all specified query conditions.
To facilitate evaluation of ERP, we construct and publicly release Exact Retrieval Question Answering (ERQA), a large-scale dataset comprising $120{,}000$ fact-oriented QA pairs, each involving complex conditions, spanning $20$ diverse domains.
The experimental results demonstrate that SG-RAG significantly outperforms strong baselines on ERQA, delivering absolute improvements from $20.68$ to $50.88$ points across all evaluation metrics, while maintaining reasonable computational overhead.

Paper Type: Long

Research Area: Retrieval-Augmented Language Models

Research Area Keywords: Dialogue and Interactive Systems

Contribution Types: NLP engineering experiment, Reproduction study, Data resources, Theory

Languages Studied: English, Chinese

Submission Number: 3585