@inproceedings{hoi-etal-2026-urgen,
title = "{URG}en: Uncertainty-guided Retrieval-augmented Generation for Guideline-Grounded Medical Question Answering",
author = "Hoi, Mengieong and
Zhao, Chen and
Lei, Chaoyu and
Zhou, Huifang and
Zheng, Zhedong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.184/",
pages = "3918--3936",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) achieve strong fluency in open-domain question answering, yet often hallucinate in specialized medical QA and lack reliable uncertainty quantification, posing risks in safety-critical applications. We propose Uncertainty-guided Retrieval-augmented Generation (URGen), a training-free framework for guideline-grounded medical multiple-choice QA, where authoritative clinical documents (e.g., consensus statements, treatment protocols) are available and answer correctness depends on precise evidence retrieval. URGen is a four-stage pipeline that combines adaptive retrieval depth with uncertainty calibration: (1) multi-temperature knowledge retrieval to rank candidate keypoints, (2) zero-shot adaptive retrieval depth (ZARD) that expands context when rankings are ambiguous, and contracts it when rankings are consistent, (3) multi-temperature answer generation with aggregation over candidates, and (4) entropy-based uncertainty estimation over the answer distribution to enable abstention on high-uncertainty queries. Extensive experiments on two expert-annotated ophthalmology benchmarks, Thyroid Eye Disease and Graves' Disease, show that URGen improves accuracy by 9.29{\%} and 6.19{\%} over a naive RAG-based Meditron-7B baseline, while achieving 3.01{\%} and 4.57{\%} expected calibration error (ECE). URGen is LLM-agnostic, consistently improving diverse backbones (, LLaMA-3.1 and Mistral) and providing interpretable uncertainty indicators for safety-critical deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoi-etal-2026-urgen">
<titleInfo>
<title>URGen: Uncertainty-guided Retrieval-augmented Generation for Guideline-Grounded Medical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengieong</namePart>
<namePart type="family">Hoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaoyu</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huifang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhedong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) achieve strong fluency in open-domain question answering, yet often hallucinate in specialized medical QA and lack reliable uncertainty quantification, posing risks in safety-critical applications. We propose Uncertainty-guided Retrieval-augmented Generation (URGen), a training-free framework for guideline-grounded medical multiple-choice QA, where authoritative clinical documents (e.g., consensus statements, treatment protocols) are available and answer correctness depends on precise evidence retrieval. URGen is a four-stage pipeline that combines adaptive retrieval depth with uncertainty calibration: (1) multi-temperature knowledge retrieval to rank candidate keypoints, (2) zero-shot adaptive retrieval depth (ZARD) that expands context when rankings are ambiguous, and contracts it when rankings are consistent, (3) multi-temperature answer generation with aggregation over candidates, and (4) entropy-based uncertainty estimation over the answer distribution to enable abstention on high-uncertainty queries. Extensive experiments on two expert-annotated ophthalmology benchmarks, Thyroid Eye Disease and Graves’ Disease, show that URGen improves accuracy by 9.29% and 6.19% over a naive RAG-based Meditron-7B baseline, while achieving 3.01% and 4.57% expected calibration error (ECE). URGen is LLM-agnostic, consistently improving diverse backbones (, LLaMA-3.1 and Mistral) and providing interpretable uncertainty indicators for safety-critical deployment.</abstract>
<identifier type="citekey">hoi-etal-2026-urgen</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.184/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3918</start>
<end>3936</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T URGen: Uncertainty-guided Retrieval-augmented Generation for Guideline-Grounded Medical Question Answering
%A Hoi, Mengieong
%A Zhao, Chen
%A Lei, Chaoyu
%A Zhou, Huifang
%A Zheng, Zhedong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hoi-etal-2026-urgen
%X Large language models (LLMs) achieve strong fluency in open-domain question answering, yet often hallucinate in specialized medical QA and lack reliable uncertainty quantification, posing risks in safety-critical applications. We propose Uncertainty-guided Retrieval-augmented Generation (URGen), a training-free framework for guideline-grounded medical multiple-choice QA, where authoritative clinical documents (e.g., consensus statements, treatment protocols) are available and answer correctness depends on precise evidence retrieval. URGen is a four-stage pipeline that combines adaptive retrieval depth with uncertainty calibration: (1) multi-temperature knowledge retrieval to rank candidate keypoints, (2) zero-shot adaptive retrieval depth (ZARD) that expands context when rankings are ambiguous, and contracts it when rankings are consistent, (3) multi-temperature answer generation with aggregation over candidates, and (4) entropy-based uncertainty estimation over the answer distribution to enable abstention on high-uncertainty queries. Extensive experiments on two expert-annotated ophthalmology benchmarks, Thyroid Eye Disease and Graves’ Disease, show that URGen improves accuracy by 9.29% and 6.19% over a naive RAG-based Meditron-7B baseline, while achieving 3.01% and 4.57% expected calibration error (ECE). URGen is LLM-agnostic, consistently improving diverse backbones (, LLaMA-3.1 and Mistral) and providing interpretable uncertainty indicators for safety-critical deployment.
%U https://aclanthology.org/2026.findings-emnlp.184/
%P 3918-3936
Markdown (Informal)
[URGen: Uncertainty-guided Retrieval-augmented Generation for Guideline-Grounded Medical Question Answering](https://aclanthology.org/2026.findings-emnlp.184/) (Hoi et al., Findings 2026)
ACL