@inproceedings{chen-etal-2024-socialbench,
title = "{S}ocial{B}ench: Sociality Evaluation of Role-Playing Conversational Agents",
author = "Chen, Hongzhan and
Chen, Hehong and
Yan, Ming and
Xu, Wenshen and
Xing, Gao and
Shen, Weizhou and
Quan, Xiaojun and
Li, Chenliang and
Zhang, Ji and
Huang, Fei",
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.125",
pages = "2108--2126",
abstract = "Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge and style of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing agents at both individual and group levels of social interactions. SocialBench is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. We conduct comprehensive evaluations on this benchmark using mainstream LLMs. We find that agents excelling in individual level does not imply their proficiency in group level. Experimental results on SocialBench confirm its significance as a testbed for assessing the social interaction of role-playing agents. The benchmark is publicly accessible at https://github.com/X-PLUG/RoleInteract.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-socialbench">
<titleInfo>
<title>SocialBench: Sociality Evaluation of Role-Playing Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongzhan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hehong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenshen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gao</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhou</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</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>Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge and style of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing agents at both individual and group levels of social interactions. SocialBench is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. We conduct comprehensive evaluations on this benchmark using mainstream LLMs. We find that agents excelling in individual level does not imply their proficiency in group level. Experimental results on SocialBench confirm its significance as a testbed for assessing the social interaction of role-playing agents. The benchmark is publicly accessible at https://github.com/X-PLUG/RoleInteract.</abstract>
<identifier type="citekey">chen-etal-2024-socialbench</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.125</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2108</start>
<end>2126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SocialBench: Sociality Evaluation of Role-Playing Conversational Agents
%A Chen, Hongzhan
%A Chen, Hehong
%A Yan, Ming
%A Xu, Wenshen
%A Xing, Gao
%A Shen, Weizhou
%A Quan, Xiaojun
%A Li, Chenliang
%A Zhang, Ji
%A Huang, Fei
%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-socialbench
%X Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge and style of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing agents at both individual and group levels of social interactions. SocialBench is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. We conduct comprehensive evaluations on this benchmark using mainstream LLMs. We find that agents excelling in individual level does not imply their proficiency in group level. Experimental results on SocialBench confirm its significance as a testbed for assessing the social interaction of role-playing agents. The benchmark is publicly accessible at https://github.com/X-PLUG/RoleInteract.
%U https://aclanthology.org/2024.findings-acl.125
%P 2108-2126
Markdown (Informal)
[SocialBench: Sociality Evaluation of Role-Playing Conversational Agents](https://aclanthology.org/2024.findings-acl.125) (Chen et al., Findings 2024)
ACL
- Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, and Fei Huang. 2024. SocialBench: Sociality Evaluation of Role-Playing Conversational Agents. In Findings of the Association for Computational Linguistics ACL 2024, pages 2108–2126, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.