@inproceedings{hong-etal-2026-mate,
title = "{MATE}: Diagnosing Empathy Calibration Failures in Multi-Turn Human{--}{LLM} Interaction",
author = "Hong, Yeseon and
Choi, Junhyuk and
Kim, Minju and
Kim, Bugeun",
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.1265/",
pages = "26743--26758",
ISBN = "979-8-89176-462-0",
abstract = "Large language models are increasingly used in emotionally consequential interactions. Response-level evaluation, however, struggles to diagnose how empathy fails across turns. We introduce MATE (Multi-turn Assessment of calibraTed Empathy), a framework that evaluates empathy as a multi-turn, perception-centered process. Across two controlled studies (N=82), baseline responses exhibit disclosure-insensitive miscalibration: generic validation and formulaic tone read as hollow across turns. A prompt-level self-critique condition makes these patterns less prominent but coincides with a different failure, agreement-skewed miscalibration, where affirmation becomes insufficiently contingent on disclosure context under high persona alignment (62.5{\%} of fit participants in Study 2). Response-level analysis is consistent with a tone{--}agreement dissociation, as the condition shifts tone toward naturalness while agreement density also increases (+98{\%} under fit vs. +25{\%} under unfit). These findings reframe empathic behavior as relational calibration{---}consistency among disclosure depth, persona, and response behavior{---}rather than maximization. Response behavior itself spans tone, agreement, and contextual specificity, sub-dimensions that can drift independently."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2026-mate">
<titleInfo>
<title>MATE: Diagnosing Empathy Calibration Failures in Multi-Turn Human–LLM Interaction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yeseon</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhyuk</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minju</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bugeun</namePart>
<namePart type="family">Kim</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 are increasingly used in emotionally consequential interactions. Response-level evaluation, however, struggles to diagnose how empathy fails across turns. We introduce MATE (Multi-turn Assessment of calibraTed Empathy), a framework that evaluates empathy as a multi-turn, perception-centered process. Across two controlled studies (N=82), baseline responses exhibit disclosure-insensitive miscalibration: generic validation and formulaic tone read as hollow across turns. A prompt-level self-critique condition makes these patterns less prominent but coincides with a different failure, agreement-skewed miscalibration, where affirmation becomes insufficiently contingent on disclosure context under high persona alignment (62.5% of fit participants in Study 2). Response-level analysis is consistent with a tone–agreement dissociation, as the condition shifts tone toward naturalness while agreement density also increases (+98% under fit vs. +25% under unfit). These findings reframe empathic behavior as relational calibration—consistency among disclosure depth, persona, and response behavior—rather than maximization. Response behavior itself spans tone, agreement, and contextual specificity, sub-dimensions that can drift independently.</abstract>
<identifier type="citekey">hong-etal-2026-mate</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1265/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26743</start>
<end>26758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MATE: Diagnosing Empathy Calibration Failures in Multi-Turn Human–LLM Interaction
%A Hong, Yeseon
%A Choi, Junhyuk
%A Kim, Minju
%A Kim, Bugeun
%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 hong-etal-2026-mate
%X Large language models are increasingly used in emotionally consequential interactions. Response-level evaluation, however, struggles to diagnose how empathy fails across turns. We introduce MATE (Multi-turn Assessment of calibraTed Empathy), a framework that evaluates empathy as a multi-turn, perception-centered process. Across two controlled studies (N=82), baseline responses exhibit disclosure-insensitive miscalibration: generic validation and formulaic tone read as hollow across turns. A prompt-level self-critique condition makes these patterns less prominent but coincides with a different failure, agreement-skewed miscalibration, where affirmation becomes insufficiently contingent on disclosure context under high persona alignment (62.5% of fit participants in Study 2). Response-level analysis is consistent with a tone–agreement dissociation, as the condition shifts tone toward naturalness while agreement density also increases (+98% under fit vs. +25% under unfit). These findings reframe empathic behavior as relational calibration—consistency among disclosure depth, persona, and response behavior—rather than maximization. Response behavior itself spans tone, agreement, and contextual specificity, sub-dimensions that can drift independently.
%U https://aclanthology.org/2026.findings-emnlp.1265/
%P 26743-26758
Markdown (Informal)
[MATE: Diagnosing Empathy Calibration Failures in Multi-Turn Human–LLM Interaction](https://aclanthology.org/2026.findings-emnlp.1265/) (Hong et al., Findings 2026)
ACL