@inproceedings{deas-etal-2026-characterizing,
title = "Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models",
author = "Deas, Nicholas and
Mejia, Ivan Ernesto Perez and
Yang, Ellie and
McKeown, Kathleen",
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.2188/",
doi = "10.18653/v1/2026.acl-long.2188",
pages = "47272--47294",
ISBN = "979-8-89176-390-6",
abstract = "Prior work evaluating emotion and affective understanding in large language models (LLMs) typically rely on predetermined label sets or focus on a singular evaluation task (e.g., emotion detection). We consider affective states, referring to the much broader variety of terms people use to label their emotional experiences. We evaluate multilingual language models' understanding of affective states in English and Spanish through three different tasks: 1) {\_}identification{\_}, where models predict an affective state given text, 2) {\_}expression{\_}, where models generate text expressing a given affective state, and 3) {\_}verification{\_}, where models report whether a given term refers to an affective state. We show that performance on one task is not necessarily predictive of performance on another. Using these three tasks, we then begin to explore when and why models struggle to understand particular affective states compared to others. We examine systematic patterns in the affective state terms that are well and poorly understood by models, characterizing the working emotion vocabulary of LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deas-etal-2026-characterizing">
<titleInfo>
<title>Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Deas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Ernesto</namePart>
<namePart type="given">Perez</namePart>
<namePart type="family">Mejia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</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>Prior work evaluating emotion and affective understanding in large language models (LLMs) typically rely on predetermined label sets or focus on a singular evaluation task (e.g., emotion detection). We consider affective states, referring to the much broader variety of terms people use to label their emotional experiences. We evaluate multilingual language models’ understanding of affective states in English and Spanish through three different tasks: 1) _identification_, where models predict an affective state given text, 2) _expression_, where models generate text expressing a given affective state, and 3) _verification_, where models report whether a given term refers to an affective state. We show that performance on one task is not necessarily predictive of performance on another. Using these three tasks, we then begin to explore when and why models struggle to understand particular affective states compared to others. We examine systematic patterns in the affective state terms that are well and poorly understood by models, characterizing the working emotion vocabulary of LLMs.</abstract>
<identifier type="citekey">deas-etal-2026-characterizing</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.2188</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2188/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>47272</start>
<end>47294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models
%A Deas, Nicholas
%A Mejia, Ivan Ernesto Perez
%A Yang, Ellie
%A McKeown, Kathleen
%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 deas-etal-2026-characterizing
%X Prior work evaluating emotion and affective understanding in large language models (LLMs) typically rely on predetermined label sets or focus on a singular evaluation task (e.g., emotion detection). We consider affective states, referring to the much broader variety of terms people use to label their emotional experiences. We evaluate multilingual language models’ understanding of affective states in English and Spanish through three different tasks: 1) _identification_, where models predict an affective state given text, 2) _expression_, where models generate text expressing a given affective state, and 3) _verification_, where models report whether a given term refers to an affective state. We show that performance on one task is not necessarily predictive of performance on another. Using these three tasks, we then begin to explore when and why models struggle to understand particular affective states compared to others. We examine systematic patterns in the affective state terms that are well and poorly understood by models, characterizing the working emotion vocabulary of LLMs.
%R 10.18653/v1/2026.acl-long.2188
%U https://aclanthology.org/2026.acl-long.2188/
%U https://doi.org/10.18653/v1/2026.acl-long.2188
%P 47272-47294
Markdown (Informal)
[Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models](https://aclanthology.org/2026.acl-long.2188/) (Deas et al., ACL 2026)
ACL