mlsanityData to 7 Oct 2026

SRAG: RAG with Structured Data Improves Vector Retrieval

arXiv 2603.26670 ↗First posted 27 Jan 2026cs.IR cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

11 of 15 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata19 Jun

Other references · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  5. 2025Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiencescited by 14
  6. 2024Struct-X: Enhancing Large Language Models Reasoning with Structured Datacited by 10
  7. 2024Multi-Document Financial Question Answering using LLMscited by 6
  8. 2025AMAQA: A Metadata-based QA Dataset for RAG Systemscited by 2
  9. 2025Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contextscited by 1
  10. 2026Utilizing Metadata for Better Retrieval-Augmented Generationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Augmenting Question Answering with A Hybrid RAG Approach
  2. 2025Structured RAG for Answering Aggregative Questions
  3. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  4. 2025In-depth Analysis of Graph-based RAG in a Unified Framework
  5. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  6. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  7. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documents
  8. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions