Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang, Zengchang Qin


Abstract
Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different conventions. Retrieving from multiple knowledge sources with one fixed strategy usually leads to under-exploitation of information. To mitigate this drawback, inspired by Mix-of-Expert, we introduce Mix-of-Granularity (MoG), a method that dynamically determines the optimal granularity of a knowledge source based on input queries using a router. The router is efficiently trained with a newly proposed loss function employing soft labels. We further extend MoG to MoG-Graph (MoGG), where reference documents are pre-processed as graphs, enabling the retrieval of distantly situated snippets. Experiments demonstrate that MoG and MoGG effectively predict optimal granularity levels, significantly enhancing the performance of the RAG system in downstream tasks. The code of both MoG and MoGG will be made public.
Anthology ID:
2025.coling-main.384
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5756–5774
Language:
URL:
https://aclanthology.org/2025.coling-main.384/
DOI:
Bibkey:
Cite (ACL):
Zijie Zhong, Hanwen Liu, Xiaoya Cui, Xiaofan Zhang, and Zengchang Qin. 2025. Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5756–5774, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation (Zhong et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.384.pdf