@inproceedings{feng-etal-2025-emocharacter,
title = "{E}mo{C}haracter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues",
author = "Feng, Qiming and
Xie, Qiujie and
Wang, Xiaolong and
Li, Qingqiu and
Zhang, Yuejie and
Feng, Rui and
Zhang, Tao and
Gao, Shang",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.316/",
doi = "10.18653/v1/2025.naacl-long.316",
pages = "6218--6240",
ISBN = "979-8-89176-189-6",
abstract = "Role-playing agents (RPAs) powered by large language models (LLMs) have been widely utilized in dialogue systems for their capability to deliver personalized interactions. Current evaluations of RPAs mainly focus on personality fidelity, tone imitation, and knowledge consistency, while overlooking emotional fidelity, a key factor that affects user experience. To this end, we propose a benchmark called EmoCharacter to assess emotional fidelity of RPAs in dialogues. EmoCharacter includes two benchmark datasets (single-turn and multi-turn dialogues), three evaluation settings, and six metrics to measure the emotional fidelity between RPAs and the characters they portray. Based on EmoCharacter, we conduct extensive evaluations on RPAs powered by seven widely used LLMs with representative role-playing methods. Our empirical findings reveal that: (1) Contrary to intuition, current role-playing methods often reduce the emotional fidelity of LLMs in dialogues; (2) Enhancing the general capabilities of LLMs does not necessarily improve the emotional fidelity of RPAs; (3) Fine-tuning or In-Context Learning based on real dialogue data can enhance emotional fidelity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2025-emocharacter">
<titleInfo>
<title>EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiming</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiujie</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingqiu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuejie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Role-playing agents (RPAs) powered by large language models (LLMs) have been widely utilized in dialogue systems for their capability to deliver personalized interactions. Current evaluations of RPAs mainly focus on personality fidelity, tone imitation, and knowledge consistency, while overlooking emotional fidelity, a key factor that affects user experience. To this end, we propose a benchmark called EmoCharacter to assess emotional fidelity of RPAs in dialogues. EmoCharacter includes two benchmark datasets (single-turn and multi-turn dialogues), three evaluation settings, and six metrics to measure the emotional fidelity between RPAs and the characters they portray. Based on EmoCharacter, we conduct extensive evaluations on RPAs powered by seven widely used LLMs with representative role-playing methods. Our empirical findings reveal that: (1) Contrary to intuition, current role-playing methods often reduce the emotional fidelity of LLMs in dialogues; (2) Enhancing the general capabilities of LLMs does not necessarily improve the emotional fidelity of RPAs; (3) Fine-tuning or In-Context Learning based on real dialogue data can enhance emotional fidelity.</abstract>
<identifier type="citekey">feng-etal-2025-emocharacter</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.316</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.316/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6218</start>
<end>6240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues
%A Feng, Qiming
%A Xie, Qiujie
%A Wang, Xiaolong
%A Li, Qingqiu
%A Zhang, Yuejie
%A Feng, Rui
%A Zhang, Tao
%A Gao, Shang
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F feng-etal-2025-emocharacter
%X Role-playing agents (RPAs) powered by large language models (LLMs) have been widely utilized in dialogue systems for their capability to deliver personalized interactions. Current evaluations of RPAs mainly focus on personality fidelity, tone imitation, and knowledge consistency, while overlooking emotional fidelity, a key factor that affects user experience. To this end, we propose a benchmark called EmoCharacter to assess emotional fidelity of RPAs in dialogues. EmoCharacter includes two benchmark datasets (single-turn and multi-turn dialogues), three evaluation settings, and six metrics to measure the emotional fidelity between RPAs and the characters they portray. Based on EmoCharacter, we conduct extensive evaluations on RPAs powered by seven widely used LLMs with representative role-playing methods. Our empirical findings reveal that: (1) Contrary to intuition, current role-playing methods often reduce the emotional fidelity of LLMs in dialogues; (2) Enhancing the general capabilities of LLMs does not necessarily improve the emotional fidelity of RPAs; (3) Fine-tuning or In-Context Learning based on real dialogue data can enhance emotional fidelity.
%R 10.18653/v1/2025.naacl-long.316
%U https://aclanthology.org/2025.naacl-long.316/
%U https://doi.org/10.18653/v1/2025.naacl-long.316
%P 6218-6240
Markdown (Informal)
[EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues](https://aclanthology.org/2025.naacl-long.316/) (Feng et al., NAACL 2025)
ACL
- Qiming Feng, Qiujie Xie, Xiaolong Wang, Qingqiu Li, Yuejie Zhang, Rui Feng, Tao Zhang, and Shang Gao. 2025. EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6218–6240, Albuquerque, New Mexico. Association for Computational Linguistics.