@inproceedings{ge-etal-2026-guidetree,
title = "{G}uide{T}ree: Guideline-Induced Review Trees for Long Medical Records",
author = "Ge, Chengze and
Zhang, Ruiqing and
Wang, Yining and
Liu, Shengping and
Jiaen, Liang and
Weihuang and
Chen, Weihua",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.110/",
doi = "10.18653/v1/2026.acl-industry.110",
pages = "1589--1604",
ISBN = "979-8-89176-394-4",
abstract = "Reviewing medical records for clinical and insurance decisions must handle long, heterogeneous documents while producing consistent, traceable, guideline-compliant outcomes under strict latency and cost constraints. We propose GuideTree, which compiles textual guidelines into a fixed review tree of evidence-grounded verification primitives. GuideTree uses short per-document summaries only for routing each check to a minimal set of document types and candidates; final verification always reads full document text and returns structured evidence. The tree is induced offline via a cost-aware split-and-prune search and updated safely through regression-tested, versioned patches. Across 1,000 cases from four industrial review scenarios and four LLM backbones, GuideTree achieves 84.5{--}92.8 Macro-F1, outperforming the strongest non-expert baselines by 3.3{--}7.6 points and matching ExpertTree within 0.2{--}0.6 points (avg. 0.38). On chronic disease with Qwen3-235B-A22B-Instruct, GuideTree reduces average I/O volume to 74K input+output characters (-82{\%} vs. long-context prompting) and average latency to 22s (-83{\%} vs. long-context prompting), while reaching 99{\%} decision consistency over K=5 reruns."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ge-etal-2026-guidetree">
<titleInfo>
<title>GuideTree: Guideline-Induced Review Trees for Long Medical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengze</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiqing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yining</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengping</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Jiaen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Weihuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Reviewing medical records for clinical and insurance decisions must handle long, heterogeneous documents while producing consistent, traceable, guideline-compliant outcomes under strict latency and cost constraints. We propose GuideTree, which compiles textual guidelines into a fixed review tree of evidence-grounded verification primitives. GuideTree uses short per-document summaries only for routing each check to a minimal set of document types and candidates; final verification always reads full document text and returns structured evidence. The tree is induced offline via a cost-aware split-and-prune search and updated safely through regression-tested, versioned patches. Across 1,000 cases from four industrial review scenarios and four LLM backbones, GuideTree achieves 84.5–92.8 Macro-F1, outperforming the strongest non-expert baselines by 3.3–7.6 points and matching ExpertTree within 0.2–0.6 points (avg. 0.38). On chronic disease with Qwen3-235B-A22B-Instruct, GuideTree reduces average I/O volume to 74K input+output characters (-82% vs. long-context prompting) and average latency to 22s (-83% vs. long-context prompting), while reaching 99% decision consistency over K=5 reruns.</abstract>
<identifier type="citekey">ge-etal-2026-guidetree</identifier>
<identifier type="doi">10.18653/v1/2026.acl-industry.110</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.110/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1589</start>
<end>1604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GuideTree: Guideline-Induced Review Trees for Long Medical Records
%A Ge, Chengze
%A Zhang, Ruiqing
%A Wang, Yining
%A Liu, Shengping
%A Jiaen, Liang
%A Chen, Weihua
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%A Weihuang
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F ge-etal-2026-guidetree
%X Reviewing medical records for clinical and insurance decisions must handle long, heterogeneous documents while producing consistent, traceable, guideline-compliant outcomes under strict latency and cost constraints. We propose GuideTree, which compiles textual guidelines into a fixed review tree of evidence-grounded verification primitives. GuideTree uses short per-document summaries only for routing each check to a minimal set of document types and candidates; final verification always reads full document text and returns structured evidence. The tree is induced offline via a cost-aware split-and-prune search and updated safely through regression-tested, versioned patches. Across 1,000 cases from four industrial review scenarios and four LLM backbones, GuideTree achieves 84.5–92.8 Macro-F1, outperforming the strongest non-expert baselines by 3.3–7.6 points and matching ExpertTree within 0.2–0.6 points (avg. 0.38). On chronic disease with Qwen3-235B-A22B-Instruct, GuideTree reduces average I/O volume to 74K input+output characters (-82% vs. long-context prompting) and average latency to 22s (-83% vs. long-context prompting), while reaching 99% decision consistency over K=5 reruns.
%R 10.18653/v1/2026.acl-industry.110
%U https://aclanthology.org/2026.acl-industry.110/
%U https://doi.org/10.18653/v1/2026.acl-industry.110
%P 1589-1604
Markdown (Informal)
[GuideTree: Guideline-Induced Review Trees for Long Medical Records](https://aclanthology.org/2026.acl-industry.110/) (Ge et al., ACL 2026)
ACL
- Chengze Ge, Ruiqing Zhang, Yining Wang, Shengping Liu, Liang Jiaen, Weihuang, and Weihua Chen. 2026. GuideTree: Guideline-Induced Review Trees for Long Medical Records. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 1589–1604, San Diego, California, USA. Association for Computational Linguistics.