Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study

Xumou Zhang, Qixuan Hu, Jinman Kim, Adam G. Dunn


Abstract
The Recursive Abstractive Processing for Tree-Organized Retrieval (RAPTOR) framework deploys a hierarchical tree-structured datastore to integrate local and global context, enabling efficient handling of long documents for language models. This design is especially useful when cloud-based language models are unavailable or undesirable. For instance, with offline confidential patient records or stringent data-privacy requirements. We benchmarked RAPTOR on the QuALITY dataset and a novel Clinical Trial question-answering dataset (CTQA) drawn from over 500 000 registry entries. Experiments varied question complexity (simple vs. complex), four language models, four embedding models, and three chunking strategies. Also incorporated GPT-4o as a cloud-based baseline. Results show that, with optimal settings, RAPTOR combined with smaller local models outperforms GPT-4o on complex CTQA questions, although this gain does not extend to QuALITY. These outcomes highlight RAPTOR’s promise as a practical, locally implementable solution for long-context understanding.
Anthology ID:
2025.ranlp-1.164
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
1420–1429
Language:
URL:
https://aclanthology.org/2025.ranlp-1.164/
DOI:
Bibkey:
Cite (ACL):
Xumou Zhang, Qixuan Hu, Jinman Kim, and Adam G. Dunn. 2025. Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1420–1429, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study (Zhang et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.164.pdf