@inproceedings{chen-etal-2026-chronoclinqa,
title = "{C}hrono{C}lin{QA}: A Longitudinal Multi-Admission Benchmark for Clinical Reasoning over Electronic Health Records",
author = "Chen, Tong and
Wang, Zimu and
Fan, Dongzhe and
Chen, Luoyao and
Lian, Haoyi and
Wang, Yifan and
Yang, Zhengni and
Jiang, Zhengyong and
Sen, Procheta and
Wang, Wei and
Su, Jionglong and
Tan, Qiaoyu",
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.2235/",
pages = "47835--47860",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) have shown strong performance on medical question answering benchmarks, yet existing evaluations remain limited in assessing longitudinal clinical reasoning across multiple hospital admissions. We introduce ChronoClinQA, a large-scale benchmark for longitudinal clinical reasoning grounded in multi-admission electronic health records. Built from longitudinal discharge summaries in MIMIC-IV-Note, ChronoClinQA contains 15,067 QA pairs spanning six clinically grounded reasoning dimensions and three complementary question formats: open-ended, adversarial, and unanswerable multiple-choice questions. Each instance requires reasoning over temporally accumulated patient trajectories, with contexts averaging over 16K tokens across up to eight hospital admissions. Experiments on both general-purpose and medical LLMs reveal substantial performance degradation in longitudinal and adversarial settings, highlighting persistent challenges in integrating cross-admission evidence and in temporal clinical reasoning. Our findings position ChronoClinQA as a challenging benchmark for advancing clinically grounded long-context reasoning in medical LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-chronoclinqa">
<titleInfo>
<title>ChronoClinQA: A Longitudinal Multi-Admission Benchmark for Clinical Reasoning over Electronic Health Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongzhe</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luoyao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyi</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengni</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Procheta</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jionglong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaoyu</namePart>
<namePart type="family">Tan</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) have shown strong performance on medical question answering benchmarks, yet existing evaluations remain limited in assessing longitudinal clinical reasoning across multiple hospital admissions. We introduce ChronoClinQA, a large-scale benchmark for longitudinal clinical reasoning grounded in multi-admission electronic health records. Built from longitudinal discharge summaries in MIMIC-IV-Note, ChronoClinQA contains 15,067 QA pairs spanning six clinically grounded reasoning dimensions and three complementary question formats: open-ended, adversarial, and unanswerable multiple-choice questions. Each instance requires reasoning over temporally accumulated patient trajectories, with contexts averaging over 16K tokens across up to eight hospital admissions. Experiments on both general-purpose and medical LLMs reveal substantial performance degradation in longitudinal and adversarial settings, highlighting persistent challenges in integrating cross-admission evidence and in temporal clinical reasoning. Our findings position ChronoClinQA as a challenging benchmark for advancing clinically grounded long-context reasoning in medical LLMs.</abstract>
<identifier type="citekey">chen-etal-2026-chronoclinqa</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2235/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47835</start>
<end>47860</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChronoClinQA: A Longitudinal Multi-Admission Benchmark for Clinical Reasoning over Electronic Health Records
%A Chen, Tong
%A Wang, Zimu
%A Fan, Dongzhe
%A Chen, Luoyao
%A Lian, Haoyi
%A Wang, Yifan
%A Yang, Zhengni
%A Jiang, Zhengyong
%A Sen, Procheta
%A Wang, Wei
%A Su, Jionglong
%A Tan, Qiaoyu
%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 chen-etal-2026-chronoclinqa
%X Large language models (LLMs) have shown strong performance on medical question answering benchmarks, yet existing evaluations remain limited in assessing longitudinal clinical reasoning across multiple hospital admissions. We introduce ChronoClinQA, a large-scale benchmark for longitudinal clinical reasoning grounded in multi-admission electronic health records. Built from longitudinal discharge summaries in MIMIC-IV-Note, ChronoClinQA contains 15,067 QA pairs spanning six clinically grounded reasoning dimensions and three complementary question formats: open-ended, adversarial, and unanswerable multiple-choice questions. Each instance requires reasoning over temporally accumulated patient trajectories, with contexts averaging over 16K tokens across up to eight hospital admissions. Experiments on both general-purpose and medical LLMs reveal substantial performance degradation in longitudinal and adversarial settings, highlighting persistent challenges in integrating cross-admission evidence and in temporal clinical reasoning. Our findings position ChronoClinQA as a challenging benchmark for advancing clinically grounded long-context reasoning in medical LLMs.
%U https://aclanthology.org/2026.findings-emnlp.2235/
%P 47835-47860
Markdown (Informal)
[ChronoClinQA: A Longitudinal Multi-Admission Benchmark for Clinical Reasoning over Electronic Health Records](https://aclanthology.org/2026.findings-emnlp.2235/) (Chen et al., Findings 2026)
ACL
- Tong Chen, Zimu Wang, Dongzhe Fan, Luoyao Chen, Haoyi Lian, Yifan Wang, Zhengni Yang, Zhengyong Jiang, Procheta Sen, Wei Wang, Jionglong Su, and Qiaoyu Tan. 2026. ChronoClinQA: A Longitudinal Multi-Admission Benchmark for Clinical Reasoning over Electronic Health Records. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 47835–47860, Budapest, Hungary. Association for Computational Linguistics.