A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications

Kwon, Mincheol; Bang, Jimin; Hwang, Seyoung; Jang, Junghoon; Lee, Woosin

doi:10.3390/electronics14040659

Open AccessArticle

A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications

by

Mincheol Kwon

^1,†,

Jimin Bang

^1,†,

Seyoung Hwang

^1,†,

Junghoon Jang

² and

Woosin Lee

^1,*

¹

Department of Computer and Information Engineering, Kwangwoon University, Seoul 01897, Republic of Korea

²

AI Research Institute, WISEnut Co., Ltd., Seongnam-si 13493, Republic of Korea

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Electronics 2025, 14(4), 659; https://doi.org/10.3390/electronics14040659

Submission received: 16 January 2025 / Revised: 3 February 2025 / Accepted: 6 February 2025 / Published: 8 February 2025

Download

Browse Figures

Versions Notes

Abstract

Commercial multi-document question-answering (QA) applications require a high multi-document retrieval performance, while simultaneously minimizing Application Programming Interface (API) usage costs of large language models (LLMs) and system complexity. To address this need, we designed the Dynamic-Selection-based, Retrieval-Augmented Generation (DS-RAG) framework, which consists of two key modules: an Entity-Preserving Question Decomposition (EPQD) module that effectively decomposes questions while preserving the entities of the original user’s question to reduce unnecessary retrieval and enhance performance, and a Dynamic Input Context Selection (DICS) module that optimizes the LLM input context based on the content of the user’s question, thereby minimizing API usage. We evaluated the proposed framework on a newly constructed dataset containing questions that require up to four multi-document retrievals. Experimental results demonstrated the new framework’s superior performance in terms of retrieval quality, input context optimization, and final answer generation compared to existing approaches. Consequently, the DS-RAG framework can be leveraged to develop domain-specific commercial QA applications in the future.

Keywords: retrieval-augmented generation; question-answering; multi-document question; multi-document retrieval; graph embedding; prompt engineering; question decomposition; knowledge graph

Share and Cite

MDPI and ACS Style

Kwon, M.; Bang, J.; Hwang, S.; Jang, J.; Lee, W. A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications. Electronics 2025, 14, 659. https://doi.org/10.3390/electronics14040659

AMA Style

Kwon M, Bang J, Hwang S, Jang J, Lee W. A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications. Electronics. 2025; 14(4):659. https://doi.org/10.3390/electronics14040659

Chicago/Turabian Style

Kwon, Mincheol, Jimin Bang, Seyoung Hwang, Junghoon Jang, and Woosin Lee. 2025. "A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications" Electronics 14, no. 4: 659. https://doi.org/10.3390/electronics14040659

APA Style

Kwon, M., Bang, J., Hwang, S., Jang, J., & Lee, W. (2025). A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications. Electronics, 14(4), 659. https://doi.org/10.3390/electronics14040659

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

A Dynamic-Selection-Based, Retrieval-Augmented Generation Framework: Enhancing Multi-Document Question-Answering for Commercial Applications

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI