@inproceedings{xu-zhang-2026-c,
title = "{C}-{V}oices{C}ompass: Evaluating Value Alignment of {LLM}s with {C}hinese Social Values",
author = "Xu, Yuemei and
Zhang, Han",
editor = "Xiong, Deyi and
Branco, Ant{\'o}nio and
Zhang, Hongming and
Dong, Yue and
Wang, Benyou and
Zhang, Wenxuan and
Zhou, Li and
Zheng, Jingting",
booktitle = "Proceedings of the First Workshop on Pluralistic Value Alignment of {LLM}s",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.plurvallm-1.12/",
pages = "165--175",
ISBN = "979-8-89176-453-8",
abstract = "With the widespread deployment of Large Language Models (LLMs), safety evaluation within diverse cultural value contexts has emerged as a critical issue in AI safety research. Existing studies predominantly rely on Western value systems, such as Schwartz{'}s theory of basic values, lacking systematic evaluation frameworks tailored to Chinese cultural values. To address this gap, C-VoicesCompass, a value alignment evaluation framework for LLMs is proposed oriented toward Chinese Social Values (CSV). The framework aims to assess the degree of LLM alignment across 12 CSV dimensions, and constructs the first human-annotated dataset, C-Voices to cover all 12 CSV dimensions, serving as a benchmark to investigate the self-annotation capacities of LLMs. Second, a lightweight value evaluator, C-VoicesEvaluator, is trained by employing an asymmetric loss function to enhance quantitative assessment precision. Finally, a value-oriented evaluation question set is developed to induce value-related responses from LLMs, enabling a systematic alignment evaluation. Experimental results show that the proposed multi-round cross-correction annotation strategy achieves annotation quality close to human annotation. Evaluations on eight mainstream LLMs reveal significant disparities in alignment and distinct value expression tendencies across the 12 dimensions. The evaluation framework has been developed for public testing at https://cvoices.net."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-zhang-2026-c">
<titleInfo>
<title>C-VoicesCompass: Evaluating Value Alignment of LLMs with Chinese Social Values</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuemei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benyou</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingting</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-453-8</identifier>
</relatedItem>
<abstract>With the widespread deployment of Large Language Models (LLMs), safety evaluation within diverse cultural value contexts has emerged as a critical issue in AI safety research. Existing studies predominantly rely on Western value systems, such as Schwartz’s theory of basic values, lacking systematic evaluation frameworks tailored to Chinese cultural values. To address this gap, C-VoicesCompass, a value alignment evaluation framework for LLMs is proposed oriented toward Chinese Social Values (CSV). The framework aims to assess the degree of LLM alignment across 12 CSV dimensions, and constructs the first human-annotated dataset, C-Voices to cover all 12 CSV dimensions, serving as a benchmark to investigate the self-annotation capacities of LLMs. Second, a lightweight value evaluator, C-VoicesEvaluator, is trained by employing an asymmetric loss function to enhance quantitative assessment precision. Finally, a value-oriented evaluation question set is developed to induce value-related responses from LLMs, enabling a systematic alignment evaluation. Experimental results show that the proposed multi-round cross-correction annotation strategy achieves annotation quality close to human annotation. Evaluations on eight mainstream LLMs reveal significant disparities in alignment and distinct value expression tendencies across the 12 dimensions. The evaluation framework has been developed for public testing at https://cvoices.net.</abstract>
<identifier type="citekey">xu-zhang-2026-c</identifier>
<location>
<url>https://aclanthology.org/2026.plurvallm-1.12/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>165</start>
<end>175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T C-VoicesCompass: Evaluating Value Alignment of LLMs with Chinese Social Values
%A Xu, Yuemei
%A Zhang, Han
%Y Xiong, Deyi
%Y Branco, António
%Y Zhang, Hongming
%Y Dong, Yue
%Y Wang, Benyou
%Y Zhang, Wenxuan
%Y Zhou, Li
%Y Zheng, Jingting
%S Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-453-8
%F xu-zhang-2026-c
%X With the widespread deployment of Large Language Models (LLMs), safety evaluation within diverse cultural value contexts has emerged as a critical issue in AI safety research. Existing studies predominantly rely on Western value systems, such as Schwartz’s theory of basic values, lacking systematic evaluation frameworks tailored to Chinese cultural values. To address this gap, C-VoicesCompass, a value alignment evaluation framework for LLMs is proposed oriented toward Chinese Social Values (CSV). The framework aims to assess the degree of LLM alignment across 12 CSV dimensions, and constructs the first human-annotated dataset, C-Voices to cover all 12 CSV dimensions, serving as a benchmark to investigate the self-annotation capacities of LLMs. Second, a lightweight value evaluator, C-VoicesEvaluator, is trained by employing an asymmetric loss function to enhance quantitative assessment precision. Finally, a value-oriented evaluation question set is developed to induce value-related responses from LLMs, enabling a systematic alignment evaluation. Experimental results show that the proposed multi-round cross-correction annotation strategy achieves annotation quality close to human annotation. Evaluations on eight mainstream LLMs reveal significant disparities in alignment and distinct value expression tendencies across the 12 dimensions. The evaluation framework has been developed for public testing at https://cvoices.net.
%U https://aclanthology.org/2026.plurvallm-1.12/
%P 165-175
Markdown (Informal)
[C-VoicesCompass: Evaluating Value Alignment of LLMs with Chinese Social Values](https://aclanthology.org/2026.plurvallm-1.12/) (Xu & Zhang, PlurVA-LLM 2026)
ACL