English

Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents

Computation and Language 2026-05-26 v1 Machine Learning

Abstract

Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge during generation, but existing text-based and graph-based RAG methods often struggle with noisy or irrelevant contexts. In this work, we propose Structure-aware Retrieval Augmented Generation (SA-RAG), which uses tables as an intermediate structured representation to provide a compact and controllable interface that reduces noise while preserving essential information. We introduce a quality-aware table metadata generation framework that models metadata normalization and effectiveness, improving metadata quality and downstream performance. Furthermore, we explore both training-free and training-based table generation methods. Generation validation and direct preference optimization further improve table quality while maintaining semantic and structural consistency. Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines. Our code is publicly available at a public repository.

Keywords

Cite

@article{arxiv.2605.24366,
  title  = {Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents},
  author = {Kaiqiao Han and LuAn Tang and Renliang Sun and Peng Yuan and Wei Cheng and Haoyu Wang and Wei Wang and Yizhou Sun and Haifeng Chen},
  journal= {arXiv preprint arXiv:2605.24366},
  year   = {2026}
}