@inproceedings{guo-etal-2026-trustworthy,
title = "Trustworthy Medical {LLM}s via {B}ayesian Belief Updating",
author = "Guo, Mengyao and
Xie, Shufang and
Chen, Xiuying and
Li, Shuqi and
Jiang, Hao and
Du, Bo and
Yan, Rui",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1678/",
pages = "38183--38198",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) show strong potential in medical QA, but still suffer from hallucinations in multi-step clinical reasoning. Existing methods fail to assess confidence at intermediate steps or reliably integrate external knowledge, leading to propagated errors and misleading conclusions. Inspired by Bayesian inference logic in clinical diagnosis, we propose BELIEF, a Bayesian Evidence Leveraged InfErence Framework that enables LLMs to perform reliable medical reasoning through dynamic belief assessment and knowledge-augmented disambiguation. First, the Bayesian Belief Updating Module (BBUM) treats diagnostic hypotheses as prior probabilities and calculates posterior probabilities based on observed clinical evidence, preventing early-stage error propagation with statistical rigor. Second, the Dynamic Evidence Retrieval Module (DERM) autonomously queries external medical databases to resolve ambiguity when the posterior belief exhibits high entropy. Experiments across 7 datasets and 2 LLM backbones show that BELIEF significantly improves diagnostic accuracy, enhances interpretability, and mitigates hallucinations through explicit probabilistic updates."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-trustworthy">
<titleInfo>
<title>Trustworthy Medical LLMs via Bayesian Belief Updating</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengyao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shufang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) show strong potential in medical QA, but still suffer from hallucinations in multi-step clinical reasoning. Existing methods fail to assess confidence at intermediate steps or reliably integrate external knowledge, leading to propagated errors and misleading conclusions. Inspired by Bayesian inference logic in clinical diagnosis, we propose BELIEF, a Bayesian Evidence Leveraged InfErence Framework that enables LLMs to perform reliable medical reasoning through dynamic belief assessment and knowledge-augmented disambiguation. First, the Bayesian Belief Updating Module (BBUM) treats diagnostic hypotheses as prior probabilities and calculates posterior probabilities based on observed clinical evidence, preventing early-stage error propagation with statistical rigor. Second, the Dynamic Evidence Retrieval Module (DERM) autonomously queries external medical databases to resolve ambiguity when the posterior belief exhibits high entropy. Experiments across 7 datasets and 2 LLM backbones show that BELIEF significantly improves diagnostic accuracy, enhances interpretability, and mitigates hallucinations through explicit probabilistic updates.</abstract>
<identifier type="citekey">guo-etal-2026-trustworthy</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1678/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>38183</start>
<end>38198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trustworthy Medical LLMs via Bayesian Belief Updating
%A Guo, Mengyao
%A Xie, Shufang
%A Chen, Xiuying
%A Li, Shuqi
%A Jiang, Hao
%A Du, Bo
%A Yan, Rui
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F guo-etal-2026-trustworthy
%X Large Language Models (LLMs) show strong potential in medical QA, but still suffer from hallucinations in multi-step clinical reasoning. Existing methods fail to assess confidence at intermediate steps or reliably integrate external knowledge, leading to propagated errors and misleading conclusions. Inspired by Bayesian inference logic in clinical diagnosis, we propose BELIEF, a Bayesian Evidence Leveraged InfErence Framework that enables LLMs to perform reliable medical reasoning through dynamic belief assessment and knowledge-augmented disambiguation. First, the Bayesian Belief Updating Module (BBUM) treats diagnostic hypotheses as prior probabilities and calculates posterior probabilities based on observed clinical evidence, preventing early-stage error propagation with statistical rigor. Second, the Dynamic Evidence Retrieval Module (DERM) autonomously queries external medical databases to resolve ambiguity when the posterior belief exhibits high entropy. Experiments across 7 datasets and 2 LLM backbones show that BELIEF significantly improves diagnostic accuracy, enhances interpretability, and mitigates hallucinations through explicit probabilistic updates.
%U https://aclanthology.org/2026.emnlp-main.1678/
%P 38183-38198
Markdown (Informal)
[Trustworthy Medical LLMs via Bayesian Belief Updating](https://aclanthology.org/2026.emnlp-main.1678/) (Guo et al., EMNLP 2026)
ACL
- Mengyao Guo, Shufang Xie, Xiuying Chen, Shuqi Li, Hao Jiang, Bo Du, and Rui Yan. 2026. Trustworthy Medical LLMs via Bayesian Belief Updating. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 38183–38198, Budapest, Hungary. Association for Computational Linguistics.