SRAG: RAG with Structured Data Improves Vector Retrieval
This addresses the limitation of similarity-based retrieval in RAG systems for users needing more accurate and diverse information retrieval, though it appears incremental as it builds on existing RAG methods.
The paper tackles the problem of improving retrieval in Retrieval Augmented Generation (RAG) by proposing Structured RAG (SRAG), which adds structured information like topics and semantic tags to queries and chunks, resulting in a 30% improvement in answer quality scores in question answering systems.
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.