FreeChunker: A Cross-Granularity Chunking Framework

Zhang Wenxuan, Yuan-Hao Jiang, Yang Cao, Yonghe Wu


Abstract
Chunking strategies significantly impact the effectiveness of Retrieval-Augmented Generation (RAG) systems. Existing methods operate within fixed-granularity paradigms that rely on static boundary identification, limiting their adaptability to diverse query requirements. This paper presents FreeChunker, a Cross-Granularity Encoding Framework that fundamentally transforms the traditional chunking paradigm: the framework treats sentences as atomic units and shifts from static chunk segmentation to flexible retrieval supporting arbitrary sentence combinations. This paradigm shift not only significantly avoids the computational overhead required for semantic boundary detection, but also enhances adaptability to complex queries. Experimental evaluation on LongBench V2 demonstrates that FreeChunker possesses significant advantages in both retrieval performance and time efficiency compared to existing chunking methods. The pre-trained models and codes are available at https://github.com/mazehart/FreeChunker.
Anthology ID:
2026.findings-acl.730
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14853–14865
Language:
URL:
https://aclanthology.org/2026.findings-acl.730/
DOI:
Bibkey:
Cite (ACL):
Zhang Wenxuan, Yuan-Hao Jiang, Yang Cao, and Yonghe Wu. 2026. FreeChunker: A Cross-Granularity Chunking Framework. In Findings of the Association for Computational Linguistics: ACL 2026, pages 14853–14865, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
FreeChunker: A Cross-Granularity Chunking Framework (Wenxuan et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.730.pdf
Checklist:
 2026.findings-acl.730.checklist.pdf