@inproceedings{zhang-etal-2026-medeq,
title = "{M}ed{EQ}: A Clinical Emotional Intelligence Benchmark and Rubric-Guided Reinforcement Learning for Patient-Centric Medical {LLM}s",
author = "Zhang, Yiming and
Yang, Xiaoyan and
Xu, Yanchao and
Deng, Jiayi and
Ma, Yingfan and
Gao, Lirong and
Gu, Yanmei and
Zhengkaiya and
Song, Bowen and
Gu, Jinjie and
Zhao, Junbo",
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.1101/",
pages = "23279--23300",
ISBN = "979-8-89176-462-0",
abstract = "Patient-facing medical LLMs are typically evaluated for clinical knowledge and safety, but clinically correct answers can still fail patients by missing fear, mishandling uncertainty, or offering emotionally unsafe reassurance. We introduce MedEQ, a benchmark for clinical emotional intelligence in medical communication. MedEQ includes 413 clinically grounded consultation scenarios across 51 specialties and 7,336 expert-refined rubric items over 21 core dimensions. These expert-validated rubrics operationalize emotional cue recognition, empathic adequacy, ethical emotional regulation, and affective safety, enabling diagnostic evaluation rather than a single holistic empathy score. Using an LLM-as-judge rubric pipeline, we find that strong contemporary models often handle surface compassion, safety, and response structure, yet remain weak on deeper emotional inference, personalization, mixed emotions, cultural context, and real-time responses to illness-related distress. We further conduct a proof-of-concept rubric-guided reinforcement learning study, showing that MedEQ-derived rubric signals can transfer to an independent emotional intelligence benchmark: rubric-guided training of Qwen3-32B improves EQ-Bench performance from 42.42 to 81.49 while preserving or slightly improving standard medical benchmark scores. MedEQ therefore makes clinical emotional intelligence measurable and decomposable, and provides evidence that expert-refined rubrics can support the evaluation and improvement of patient-facing medical AI."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-medeq">
<titleInfo>
<title>MedEQ: A Clinical Emotional Intelligence Benchmark and Rubric-Guided Reinforcement Learning for Patient-Centric Medical LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanchao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingfan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lirong</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanmei</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Zhengkaiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinjie</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junbo</namePart>
<namePart type="family">Zhao</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>Patient-facing medical LLMs are typically evaluated for clinical knowledge and safety, but clinically correct answers can still fail patients by missing fear, mishandling uncertainty, or offering emotionally unsafe reassurance. We introduce MedEQ, a benchmark for clinical emotional intelligence in medical communication. MedEQ includes 413 clinically grounded consultation scenarios across 51 specialties and 7,336 expert-refined rubric items over 21 core dimensions. These expert-validated rubrics operationalize emotional cue recognition, empathic adequacy, ethical emotional regulation, and affective safety, enabling diagnostic evaluation rather than a single holistic empathy score. Using an LLM-as-judge rubric pipeline, we find that strong contemporary models often handle surface compassion, safety, and response structure, yet remain weak on deeper emotional inference, personalization, mixed emotions, cultural context, and real-time responses to illness-related distress. We further conduct a proof-of-concept rubric-guided reinforcement learning study, showing that MedEQ-derived rubric signals can transfer to an independent emotional intelligence benchmark: rubric-guided training of Qwen3-32B improves EQ-Bench performance from 42.42 to 81.49 while preserving or slightly improving standard medical benchmark scores. MedEQ therefore makes clinical emotional intelligence measurable and decomposable, and provides evidence that expert-refined rubrics can support the evaluation and improvement of patient-facing medical AI.</abstract>
<identifier type="citekey">zhang-etal-2026-medeq</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1101/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>23279</start>
<end>23300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedEQ: A Clinical Emotional Intelligence Benchmark and Rubric-Guided Reinforcement Learning for Patient-Centric Medical LLMs
%A Zhang, Yiming
%A Yang, Xiaoyan
%A Xu, Yanchao
%A Deng, Jiayi
%A Ma, Yingfan
%A Gao, Lirong
%A Gu, Yanmei
%A Song, Bowen
%A Gu, Jinjie
%A Zhao, Junbo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%A Zhengkaiya
%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 zhang-etal-2026-medeq
%X Patient-facing medical LLMs are typically evaluated for clinical knowledge and safety, but clinically correct answers can still fail patients by missing fear, mishandling uncertainty, or offering emotionally unsafe reassurance. We introduce MedEQ, a benchmark for clinical emotional intelligence in medical communication. MedEQ includes 413 clinically grounded consultation scenarios across 51 specialties and 7,336 expert-refined rubric items over 21 core dimensions. These expert-validated rubrics operationalize emotional cue recognition, empathic adequacy, ethical emotional regulation, and affective safety, enabling diagnostic evaluation rather than a single holistic empathy score. Using an LLM-as-judge rubric pipeline, we find that strong contemporary models often handle surface compassion, safety, and response structure, yet remain weak on deeper emotional inference, personalization, mixed emotions, cultural context, and real-time responses to illness-related distress. We further conduct a proof-of-concept rubric-guided reinforcement learning study, showing that MedEQ-derived rubric signals can transfer to an independent emotional intelligence benchmark: rubric-guided training of Qwen3-32B improves EQ-Bench performance from 42.42 to 81.49 while preserving or slightly improving standard medical benchmark scores. MedEQ therefore makes clinical emotional intelligence measurable and decomposable, and provides evidence that expert-refined rubrics can support the evaluation and improvement of patient-facing medical AI.
%U https://aclanthology.org/2026.findings-emnlp.1101/
%P 23279-23300
Markdown (Informal)
[MedEQ: A Clinical Emotional Intelligence Benchmark and Rubric-Guided Reinforcement Learning for Patient-Centric Medical LLMs](https://aclanthology.org/2026.findings-emnlp.1101/) (Zhang et al., Findings 2026)
ACL
- Yiming Zhang, Xiaoyan Yang, Yanchao Xu, Jiayi Deng, Yingfan Ma, Lirong Gao, Yanmei Gu, Zhengkaiya, Bowen Song, Jinjie Gu, and Junbo Zhao. 2026. MedEQ: A Clinical Emotional Intelligence Benchmark and Rubric-Guided Reinforcement Learning for Patient-Centric Medical LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 23279–23300, Budapest, Hungary. Association for Computational Linguistics.