@inproceedings{chen-etal-2024-emotionqueen,
title = "{E}motion{Q}ueen: A Benchmark for Evaluating Empathy of Large Language Models",
author = "Chen, Yuyan and
Yan, Songzhou and
Liu, Sijia and
Li, Yueze and
Xiao, Yanghua",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.128",
doi = "10.18653/v1/2024.findings-acl.128",
pages = "2149--2176",
abstract = "Emotional intelligence in large language models (LLMs) is of great importance in Natural Language Processing. However, the previous research mainly focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs{'} overall emotional intelligence. Therefore, this paper presents a novel framework named EmotionQueen for evaluating the emotional intelligence of LLMs. The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition. LLMs are requested to recognize important event or implicit emotions and generate empathetic response.We also design two metrics to evaluate LLMs{'} capabilities in recognition and response for emotion-related statements. Experiments yield significant conclusions about LLMs{'} capabilities and limitations in emotion intelligence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-emotionqueen">
<titleInfo>
<title>EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuyan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songzhou</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sijia</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotional intelligence in large language models (LLMs) is of great importance in Natural Language Processing. However, the previous research mainly focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs’ overall emotional intelligence. Therefore, this paper presents a novel framework named EmotionQueen for evaluating the emotional intelligence of LLMs. The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition. LLMs are requested to recognize important event or implicit emotions and generate empathetic response.We also design two metrics to evaluate LLMs’ capabilities in recognition and response for emotion-related statements. Experiments yield significant conclusions about LLMs’ capabilities and limitations in emotion intelligence.</abstract>
<identifier type="citekey">chen-etal-2024-emotionqueen</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.128</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.128</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2149</start>
<end>2176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models
%A Chen, Yuyan
%A Yan, Songzhou
%A Liu, Sijia
%A Li, Yueze
%A Xiao, Yanghua
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F chen-etal-2024-emotionqueen
%X Emotional intelligence in large language models (LLMs) is of great importance in Natural Language Processing. However, the previous research mainly focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs’ overall emotional intelligence. Therefore, this paper presents a novel framework named EmotionQueen for evaluating the emotional intelligence of LLMs. The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition. LLMs are requested to recognize important event or implicit emotions and generate empathetic response.We also design two metrics to evaluate LLMs’ capabilities in recognition and response for emotion-related statements. Experiments yield significant conclusions about LLMs’ capabilities and limitations in emotion intelligence.
%R 10.18653/v1/2024.findings-acl.128
%U https://aclanthology.org/2024.findings-acl.128
%U https://doi.org/10.18653/v1/2024.findings-acl.128
%P 2149-2176
Markdown (Informal)
[EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models](https://aclanthology.org/2024.findings-acl.128) (Chen et al., Findings 2024)
ACL