@inproceedings{jafari-etal-2026-disentangling,
title = "Disentangling Emotion Understanding and Generation in Large Language Models",
author = "Jafari, Sadegh and
Lefever, Els and
Hoste, Veronique",
editor = "Barnes, Jeremy and
Barriere, Valentin and
De Clercq, Orph{\'e}e and
Klinger, Roman and
Nouri, C{\'e}lia and
Nozza, Debora and
Singh, Pranaydeep",
booktitle = "The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis ({WASSA} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wassa-1.14/",
pages = "161--171",
ISBN = "979-8-89176-378-4",
abstract = "Large language models (LLMs) have demonstrated strong performance on emotion understanding tasks, yet their ability to faithfully generate emotionally aligned text remains less well understood.We propose a semantic evaluation framework that jointly assesses emotion understanding, emotion generation, and internal consistency, using a VAE-based emotion cost matrix that captures graded semantic similarity between emotion categories.Our framework introduces four complementary metrics that disentangle baseline understanding, human-perceived emotion in generated text, generation quality, and model consistency.Experimental results show that while understanding and consistency scores are highly correlated, emotion generation exhibits substantially weaker correlations with these metrics.These findings motivate the development of specialized evaluation protocols that independently measure emotional understanding and generation, enabling more reliable assessments of LLM emotional intelligence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jafari-etal-2026-disentangling">
<titleInfo>
<title>Disentangling Emotion Understanding and Generation in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadegh</namePart>
<namePart type="family">Jafari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Célia</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranaydeep</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-378-4</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated strong performance on emotion understanding tasks, yet their ability to faithfully generate emotionally aligned text remains less well understood.We propose a semantic evaluation framework that jointly assesses emotion understanding, emotion generation, and internal consistency, using a VAE-based emotion cost matrix that captures graded semantic similarity between emotion categories.Our framework introduces four complementary metrics that disentangle baseline understanding, human-perceived emotion in generated text, generation quality, and model consistency.Experimental results show that while understanding and consistency scores are highly correlated, emotion generation exhibits substantially weaker correlations with these metrics.These findings motivate the development of specialized evaluation protocols that independently measure emotional understanding and generation, enabling more reliable assessments of LLM emotional intelligence.</abstract>
<identifier type="citekey">jafari-etal-2026-disentangling</identifier>
<location>
<url>https://aclanthology.org/2026.wassa-1.14/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>161</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disentangling Emotion Understanding and Generation in Large Language Models
%A Jafari, Sadegh
%A Lefever, Els
%A Hoste, Veronique
%Y Barnes, Jeremy
%Y Barriere, Valentin
%Y De Clercq, Orphée
%Y Klinger, Roman
%Y Nouri, Célia
%Y Nozza, Debora
%Y Singh, Pranaydeep
%S The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-378-4
%F jafari-etal-2026-disentangling
%X Large language models (LLMs) have demonstrated strong performance on emotion understanding tasks, yet their ability to faithfully generate emotionally aligned text remains less well understood.We propose a semantic evaluation framework that jointly assesses emotion understanding, emotion generation, and internal consistency, using a VAE-based emotion cost matrix that captures graded semantic similarity between emotion categories.Our framework introduces four complementary metrics that disentangle baseline understanding, human-perceived emotion in generated text, generation quality, and model consistency.Experimental results show that while understanding and consistency scores are highly correlated, emotion generation exhibits substantially weaker correlations with these metrics.These findings motivate the development of specialized evaluation protocols that independently measure emotional understanding and generation, enabling more reliable assessments of LLM emotional intelligence.
%U https://aclanthology.org/2026.wassa-1.14/
%P 161-171
Markdown (Informal)
[Disentangling Emotion Understanding and Generation in Large Language Models](https://aclanthology.org/2026.wassa-1.14/) (Jafari et al., WASSA 2026)
ACL