@inproceedings{zhang-etal-2026-inflated,
title = "Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation",
author = "Zhang, Xiangxu and
Li, Lei and
Zhou, Yanyun and
Zhou, Xiao and
Zhang, Yingying and
Wu, Xian",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1218/",
pages = "26454--26493",
ISBN = "979-8-89176-390-6",
abstract = "Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) remain limited in capturing key challenges of clinical diagnostic scenarios. Most rely on benchmarks derived from public exams, raising contamination bias that can inflate performance, and they overlook the confounded nature of real consultations beyond textbook cases. Recent dynamic evaluations offer a promising alternative, but often remain insufficient for diagnosis-oriented benchmarking, with limited coverage of clinically grounded confounders and trustworthiness beyond accuracy. To address these gaps, we propose DyReMe, a dynamic benchmark for medical diagnostics that provides a controlled and scalable stress test of diagnostic robustness. Unlike static exam-style questions, DyReMe generates fresh, consultation-style cases that incorporate clinically grounded confounders, such as differential diagnoses and common misdiagnosis factors. It also varies expression styles to capture heterogeneous patient-style descriptions. Beyond accuracy, DyReMe evaluates LLMs on three additional clinically relevant dimensions: veracity, helpfulness, and consistency. Our experiments show that this dynamic approach yields more challenging assessments and exposes substantial weaknesses of stateof-the-art LLMs under clinically confounded diagnostic settings. These findings highlight the urgent need for evaluation frameworks that better assess trustworthy medical diagnostics under clinically grounded confounders."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-inflated">
<titleInfo>
<title>Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiangxu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Wu</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 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) remain limited in capturing key challenges of clinical diagnostic scenarios. Most rely on benchmarks derived from public exams, raising contamination bias that can inflate performance, and they overlook the confounded nature of real consultations beyond textbook cases. Recent dynamic evaluations offer a promising alternative, but often remain insufficient for diagnosis-oriented benchmarking, with limited coverage of clinically grounded confounders and trustworthiness beyond accuracy. To address these gaps, we propose DyReMe, a dynamic benchmark for medical diagnostics that provides a controlled and scalable stress test of diagnostic robustness. Unlike static exam-style questions, DyReMe generates fresh, consultation-style cases that incorporate clinically grounded confounders, such as differential diagnoses and common misdiagnosis factors. It also varies expression styles to capture heterogeneous patient-style descriptions. Beyond accuracy, DyReMe evaluates LLMs on three additional clinically relevant dimensions: veracity, helpfulness, and consistency. Our experiments show that this dynamic approach yields more challenging assessments and exposes substantial weaknesses of stateof-the-art LLMs under clinically confounded diagnostic settings. These findings highlight the urgent need for evaluation frameworks that better assess trustworthy medical diagnostics under clinically grounded confounders.</abstract>
<identifier type="citekey">zhang-etal-2026-inflated</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1218/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>26454</start>
<end>26493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
%A Zhang, Xiangxu
%A Li, Lei
%A Zhou, Yanyun
%A Zhou, Xiao
%A Zhang, Yingying
%A Wu, Xian
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F zhang-etal-2026-inflated
%X Medical diagnostics is a high-stakes and complex domain that is critical to patient care. However, current evaluations of large language models (LLMs) remain limited in capturing key challenges of clinical diagnostic scenarios. Most rely on benchmarks derived from public exams, raising contamination bias that can inflate performance, and they overlook the confounded nature of real consultations beyond textbook cases. Recent dynamic evaluations offer a promising alternative, but often remain insufficient for diagnosis-oriented benchmarking, with limited coverage of clinically grounded confounders and trustworthiness beyond accuracy. To address these gaps, we propose DyReMe, a dynamic benchmark for medical diagnostics that provides a controlled and scalable stress test of diagnostic robustness. Unlike static exam-style questions, DyReMe generates fresh, consultation-style cases that incorporate clinically grounded confounders, such as differential diagnoses and common misdiagnosis factors. It also varies expression styles to capture heterogeneous patient-style descriptions. Beyond accuracy, DyReMe evaluates LLMs on three additional clinically relevant dimensions: veracity, helpfulness, and consistency. Our experiments show that this dynamic approach yields more challenging assessments and exposes substantial weaknesses of stateof-the-art LLMs under clinically confounded diagnostic settings. These findings highlight the urgent need for evaluation frameworks that better assess trustworthy medical diagnostics under clinically grounded confounders.
%U https://aclanthology.org/2026.acl-long.1218/
%P 26454-26493
Markdown (Informal)
[Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation](https://aclanthology.org/2026.acl-long.1218/) (Zhang et al., ACL 2026)
ACL