# SRAG: RAG with Structured Data Improves Vector Retrieval

arXiv: https://arxiv.org/abs/2603.26670 · HTML: https://mlsanity.com/paper/2603.26670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata](https://mlsanity.com/paper/2406.13213/) (2024)
- [Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences](https://mlsanity.com/paper/2509.16189/) (2025)
- [Struct-X: Enhancing Large Language Models Reasoning with Structured Data](https://mlsanity.com/paper/2407.12522/) (2024)
- [Multi-Document Financial Question Answering using LLMs](https://mlsanity.com/paper/2411.07264/) (2024)
- [AMAQA: A Metadata-based QA Dataset for RAG Systems](https://mlsanity.com/paper/2505.13557/) (2025)
- [Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts](https://mlsanity.com/paper/2510.22956/) (2025)
- [Utilizing Metadata for Better Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.11863/) (2026)

## Abstract (arXiv)

Retrieval Augmented Generation (RAG) provides the necessary informational grounding to LLMs in the form of chunks retrieved from a vector database or through web search. RAG could also use knowledge graph triples as a means of providing factual information to an LLM. However, the retrieval is only based on representational similarity between a question and the contents. The performance of RAG depends on the numeric vector representations of the query and the chunks. To improve these representations, we propose Structured RAG (SRAG), which adds structured information to a query as well as the chunks in the form of topics, sentiments, query and chunk types (e.g., informational, quantitative), knowledge graph triples and semantic tags. Experiments indicate that this method significantly improves the retrieval process. Using GPT-5 as an LLM-as-a-judge, results show that the method improves the score given to answers in a question answering system by 30% (p-value = 2e-13) (with tighter bounds). The strongest improvement is in comparative, analytical and predictive questions. The results suggest that our method enables broader, more diverse, and episodic-style retrieval. Tail risk analysis shows that SRAG attains very large gains more often, with losses remaining minor in magnitude.