질의 조건 기반 Retrieval Unit을 적용한 검색 증강 생성 기법

A RAG Method based on Query-Conditioned Retrieval Units

초록

This paper proposes DRAG, a Retrieval-Augmented Generation (RAG) method based on query-conditioned Retrieval Units. Existing RAG systems often rely on fixed-size chunking or sliding-window methods, which do not sufficiently reflect query semantics and document structure. DRAG reformulates document segmentation as a query-conditioned retrieval unit construction task and dynamically constructs Retrieval Units by considering both query semantics and document structure. Experimental results show that DRAG improves Recall@20 by 9.0% and reduces the Redundant Context token Ratio (RTR) by 14.1% compared with Fixed Chunking, while improving F1 Score by 7.0% compared with Semantic Chunking. These results demonstrate that the proposed method effectively enhances both retrieval performance and context utilization efficiency.

키워드

RAG; retrieval unit; query-conditioned retrieval; document chunking; context utilization efficiency; .
제목
질의 조건 기반 Retrieval Unit을 적용한 검색 증강 생성 기법
제목 (타언어)
A RAG Method based on Query-Conditioned Retrieval Units
저자
김영아; 정선미; 김현주; 김창근
발행일
2026-08
유형
Y
저널명
한국정보기술학회논문지
권
24
호
8
페이지
69 ~ 80