Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913157965938688 |
|---|---|
| author | Han, Kaiqiao Tang, LuAn Sun, Renliang Yuan, Peng Cheng, Wei Wang, Haoyu Wang, Wei Sun, Yizhou Chen, Haifeng |
| author_facet | Han, Kaiqiao Tang, LuAn Sun, Renliang Yuan, Peng Cheng, Wei Wang, Haoyu Wang, Wei Sun, Yizhou Chen, Haifeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24366 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents Han, Kaiqiao Tang, LuAn Sun, Renliang Yuan, Peng Cheng, Wei Wang, Haoyu Wang, Wei Sun, Yizhou Chen, Haifeng Computation and Language Machine Learning 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. |
| title | Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2605.24366 |