SRAG: RAG with Structured Data Improves Vector Retrieval

2026-01-27 · Shalin Shah, Srikanth Ryali, Ramasubbu Venkatesh 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.

📄 PDF Abstract BibTeX arXiv:2603.26670

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Augmenting Question Answering with A Hybrid RAG Approach

2026-01-19 · Tianyi Yang, Nashrah Haque, Vaishnave Jonnalagadda, Yuya Jeremy Ong 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually r…

Question Answering

RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations

2026-02-25 · I-Hsiang Chen, Yu-Wei Liu, Tse-Yu Wu, Yu-Chien Chiang 외 arxiv

Vision-based Retrieval-Augmented Generation (VisRAG) leverages vision-language models (VLMs) to jointly retrieve relevant visual documents and generate grounded answers based on multimodal evidence. However, existing Vis…

Zero-shot Generalization

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

2026-06-16 · Amirhossein Abaskohi, Raymond Li, Gaetano Cimino, Peter West 외 arxiv

Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larg…

SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

2025-03-03 · Teng Lin, Yizhang Zhu, Yuyu Luo, Nan Tang

Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "Wha…

Question Answering RAG Retrieval Retrieval-augmented Generation

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

2026-05-15 · Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le, Duy Cao Hoang 외 arxiv

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinat…

Prompt Engineering