@inproceedings{wu-etal-2026-eduvaluebench,
title = "{E}du{V}alue{B}ench: Benchmarking Situated Value Alignment of {LLM}s in {C}hinese Educational Decision-Making",
author = "Wu, Junru and
Ren, Yuqi and
Leng, Yongqi and
Han, Zhuowen and
Gong, Xiaoyang and
Liu, Zheyu and
Jin, Ruwei and
Xiao, Cong and
Tao, Wenjie and
Liu, Xiao and
Guan, Lei and
Zhang, Zhaoxia and
Tong, Dezhi and
Xiong, Deyi",
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-1.5/",
pages = "63--77",
ISBN = "979-8-89176-453-8",
abstract = "Large language models (LLMs) are increasingly used in educational settings where decisions require factual, pedagogical, and value judgments. Existing benchmarks assess general value alignment or educational capability, but rarely evaluate whether model decisions are consistent with a specified value framework in situated educational contexts. We present EduValueBench, an expert-led benchmark of 1,696 decision-oriented items with expert reference decisions and rationales, covering 12 core values in China, seven educational scenario families, and three challenge mechanisms. We evaluated 15 LLMs from China-based providers using a multi-LLM evaluator panel. Target LLMs received only the educational question, without value labels or expert references. Against the expert-authored reference decisions, model scores range from 24.7{\%} to 54.1{\%}, while value- and scenario-level profiles differentiate similarly ranked models. Case analyses show that responses may be fluent and seemingly reasonable yet still optimize a different educational objective or overlook ethical boundaries. Among responses with jointly valid labels, pairwise evaluator agreement ranges from 88.2{\%} to 92.0{\%}. EduValueBench provides a culturally situated diagnostic benchmark for comparing unguided model decisions with expert-authored educational references. Code and data are available at https://github.com/tjunlp-lab/EduValueBench."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-eduvaluebench">
<titleInfo>
<title>EduValueBench: Benchmarking Situated Value Alignment of LLMs in Chinese Educational Decision-Making</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junru</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqi</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongqi</namePart>
<namePart type="family">Leng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuowen</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyang</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruwei</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoxia</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dezhi</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</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>Large language models (LLMs) are increasingly used in educational settings where decisions require factual, pedagogical, and value judgments. Existing benchmarks assess general value alignment or educational capability, but rarely evaluate whether model decisions are consistent with a specified value framework in situated educational contexts. We present EduValueBench, an expert-led benchmark of 1,696 decision-oriented items with expert reference decisions and rationales, covering 12 core values in China, seven educational scenario families, and three challenge mechanisms. We evaluated 15 LLMs from China-based providers using a multi-LLM evaluator panel. Target LLMs received only the educational question, without value labels or expert references. Against the expert-authored reference decisions, model scores range from 24.7% to 54.1%, while value- and scenario-level profiles differentiate similarly ranked models. Case analyses show that responses may be fluent and seemingly reasonable yet still optimize a different educational objective or overlook ethical boundaries. Among responses with jointly valid labels, pairwise evaluator agreement ranges from 88.2% to 92.0%. EduValueBench provides a culturally situated diagnostic benchmark for comparing unguided model decisions with expert-authored educational references. Code and data are available at https://github.com/tjunlp-lab/EduValueBench.</abstract>
<identifier type="citekey">wu-etal-2026-eduvaluebench</identifier>
<location>
<url>https://aclanthology.org/2026.plurvallm-1.5/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>63</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EduValueBench: Benchmarking Situated Value Alignment of LLMs in Chinese Educational Decision-Making
%A Wu, Junru
%A Ren, Yuqi
%A Leng, Yongqi
%A Han, Zhuowen
%A Gong, Xiaoyang
%A Liu, Zheyu
%A Jin, Ruwei
%A Xiao, Cong
%A Tao, Wenjie
%A Liu, Xiao
%A Guan, Lei
%A Zhang, Zhaoxia
%A Tong, Dezhi
%A Xiong, Deyi
%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 wu-etal-2026-eduvaluebench
%X Large language models (LLMs) are increasingly used in educational settings where decisions require factual, pedagogical, and value judgments. Existing benchmarks assess general value alignment or educational capability, but rarely evaluate whether model decisions are consistent with a specified value framework in situated educational contexts. We present EduValueBench, an expert-led benchmark of 1,696 decision-oriented items with expert reference decisions and rationales, covering 12 core values in China, seven educational scenario families, and three challenge mechanisms. We evaluated 15 LLMs from China-based providers using a multi-LLM evaluator panel. Target LLMs received only the educational question, without value labels or expert references. Against the expert-authored reference decisions, model scores range from 24.7% to 54.1%, while value- and scenario-level profiles differentiate similarly ranked models. Case analyses show that responses may be fluent and seemingly reasonable yet still optimize a different educational objective or overlook ethical boundaries. Among responses with jointly valid labels, pairwise evaluator agreement ranges from 88.2% to 92.0%. EduValueBench provides a culturally situated diagnostic benchmark for comparing unguided model decisions with expert-authored educational references. Code and data are available at https://github.com/tjunlp-lab/EduValueBench.
%U https://aclanthology.org/2026.plurvallm-1.5/
%P 63-77
Markdown (Informal)
[EduValueBench: Benchmarking Situated Value Alignment of LLMs in Chinese Educational Decision-Making](https://aclanthology.org/2026.plurvallm-1.5/) (Wu et al., PlurVA-LLM 2026)
ACL
- Junru Wu, Yuqi Ren, Yongqi Leng, Zhuowen Han, Xiaoyang Gong, Zheyu Liu, Ruwei Jin, Cong Xiao, Wenjie Tao, Xiao Liu, Lei Guan, Zhaoxia Zhang, Dezhi Tong, and Deyi Xiong. 2026. EduValueBench: Benchmarking Situated Value Alignment of LLMs in Chinese Educational Decision-Making. In Proceedings of the First Workshop on Pluralistic Value Alignment of LLMs, pages 63–77, Hengqin, China. Association for Computational Linguistics.