@inproceedings{zhang-etal-2025-strategies,
title = "Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with {RAPTOR}: A Benchmarking Study",
author = "Zhang, Xumou and
Hu, Qixuan and
Kim, Jinman and
Dunn, Adam G.",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.164/",
pages = "1420--1429",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-strategies">
<titleInfo>
<title>Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xumou</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qixuan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinman</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Dunn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zhang-etal-2025-strategies</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.164/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1420</start>
<end>1429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study
%A Zhang, Xumou
%A Hu, Qixuan
%A Kim, Jinman
%A Dunn, Adam G.
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F zhang-etal-2025-strategies
%X 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.
%U https://aclanthology.org/2025.ranlp-1.164/
%P 1420-1429
Markdown (Informal)
[Strategies for Efficient Retrieval-augmented Generation in Clinical Domains with RAPTOR: A Benchmarking Study](https://aclanthology.org/2025.ranlp-1.164/) (Zhang et al., RANLP 2025)
ACL