@article{ART003266057},
author={Ji-Min Bang and Woo-Sin Lee},
title={Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={11},
pages={19-27}
TY - JOUR
AU - Ji-Min Bang
AU - Woo-Sin Lee
TI - Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 11
PB - The Korean Society Of Computer And Information
SP - 19
EP - 27
SN - 1598-849X
AB - Multi-document Question Answering (Multi-document QA) is an essential component of question answering systems in real-world environments. It requires extracting and integrating the necessary information from multiple documents to generate accurate responses. The DS-RAG framework is optimized for real-world multi-document QA tasks. It improves the system’s overall accuracy and efficiency by using a document selection module that selects only the core documents retrieved after question decomposition, which are necessary for response generation. However, this process requires additional computational resources and additional training, making it difficult to apply in resource-limited environments. To address this limitation, this study proposes a Lightweight DS-RAG framework that achieves selection effects through importance-weighted query generation, thereby eliminating the need for a separate selection module. The proposed approach identifies key information within a question and generates importance-weighted queries. This enables retrieval focused on the most relevant information while maintaining both efficiency and accuracy. This approach maintains high retrieval accuracy while significantly reducing computational overhead, and can be applied in resource-constrained environments without domain-specific training. Experimental results demonstrate that the Lightweight DS-RAG framework achieves 95% of the retrieval performance of the original DS-RAG, as measured by the F1-score. Additionally, it exhibited an average performance improvement of 67.5% over RAG without a selection module. These results demonstrate that a high level of accuracy can be maintained without a separate selection module or additional training, indicating that the Lightweight DS-RAG framework can serve as a practical alternative in resource-constrained environments.
KW - Retrieval-Augmented Generation(RAG);Multi-document Question Answering;;Information Retrieval;Docuent Selection;Generation Optimization;Lightweight Model
DO -
UR -
ER -
Ji-Min Bang and Woo-Sin Lee. (2025). Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices. Journal of The Korea Society of Computer and Information, 30(11), 19-27.
Ji-Min Bang and Woo-Sin Lee. 2025, "Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices", Journal of The Korea Society of Computer and Information, vol.30, no.11 pp.19-27.
Ji-Min Bang, Woo-Sin Lee "Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices" Journal of The Korea Society of Computer and Information 30.11 pp.19-27 (2025) : 19.
Ji-Min Bang, Woo-Sin Lee. Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices. 2025; 30(11), 19-27.
Ji-Min Bang and Woo-Sin Lee. "Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 19-27.
Ji-Min Bang; Woo-Sin Lee. Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices. Journal of The Korea Society of Computer and Information, 30(11), 19-27.
Ji-Min Bang; Woo-Sin Lee. Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices. Journal of The Korea Society of Computer and Information. 2025; 30(11) 19-27.
Ji-Min Bang, Woo-Sin Lee. Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices. 2025; 30(11), 19-27.
Ji-Min Bang and Woo-Sin Lee. "Lightweight DS-RAG: A Training-Free RAG Framework for Multi-Document QA on Edge Devices" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 19-27.
