大模型
arxiv.org ·
EduFair-Bench：评估 LLM 辅导者在不同学生人口统计特征下的教学公平性
该论文提出 EduFair-Bench 基准，用于审计 LLM 辅导者的教学公平性，即辅导质量是否随学生人口统计特征系统性变化。基准结合数学、物理、化学多领域题库与受控模拟：固定 LLM 学生与每个辅导者在性别、移民背景、母语、社会经济地位四个维度的九个层级上交互，辅导质量按五项轮次级教学指标和四项对话级维度评分，评判器经 180 个辅导轮次的三标注者共识验证，偏差用配对 Wilcoxon 符号秩检验和 bootstrap 效应量置信区间度量。两项消融实验（通过姓名传递人口统计线索、辅导者与学生人口统计信息冲突）区分辅导者驱动与学生驱动的偏差。在五个辅导者上的结果显示：模型能力与人口统计公平性基本正交，最小模型最一致，四个更强辅导者均存在较大人口统计差距且无清晰的能力-公平性排序；教学专用 RL 训练重新分配而非消除偏差；语言和移民相关线索造成的差距大于性别和 SES 线索。
AI推荐理由 arXiv 新论文，提出 EduFair-Bench 基准，用多领域题库（数学、物理、化学）和受控模拟（固定 LLM 学生与各辅导者交互，覆盖性别、移民背景、母语、SES 四个维度共九个层级）审计 LLM 辅导者的教学公平性；以五项轮次级教学指标和四项对话级维度评分，LLM 评判器经 180 个辅导轮次的三标注者共识验证，并用配对 Wilcoxon 符号秩检验和 bootstrap 效应量置信区间度量偏差。核心发现：模型能力与人口统计公平性基本正交，最小模型最一致，四个更强辅导者均存在较大人口统计差距且无清晰的能力-公平性排序；教学专用 RL 训练是重新分配而非消除偏差；语言和移民相关线索造成的差距大于性别和 SES 线索。信息密度高、方法可验证，对 LLM 教育应用落地有直接参考价值；局限是仅覆盖五个辅导者、模拟学生而非真实用户。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.12949 (cs)
[Submitted on 11 Sep 2026]
Title:EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics
Authors:Jiaxu Zhao, Bahar Radmehr, Fares Fawzi, Tanya Nazaretsky, Tanja Käser
View a PDF of the paper titled EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics, by Jiaxu Zhao and 4 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) are increasingly deployed as tutors, but it is unclear whether they support all students equally well. We introduce \textbf{EduFair-Bench}, a benchmark for auditing the pedagogical fairness of LLM tutors---whether tutoring quality varies systematically with student demographics. EduFair-Bench pairs a multi-domain question bank (mathematics, physics, chemistry) with a controlled simulation in which a fixed LLM student interacts with each tutor across nine demographic levels spanning four dimensions: gender, immigration background, first language, and socioeconomic status (SES). Tutoring quality is scored on five turn-level pedagogical metrics and four conversation-level dimensions, using an LLM judge validated against three-annotator consensus on 180 tutor turns. Bias is measured via paired Wilcoxon signed-rank tests and bootstrap effect-size confidence intervals. Two ablations (demographic cues conveyed through names; conflicting demographic information between tutor and student) disentangle tutor-driven from student-driven bias. Across five tutors, we find that model capability and demographic fairness are largely orthogonal: the smallest model is the most consistent while the four more capable tutors all exhibit wide demographic gaps with no clear capability-to-fairness ordering, pedagogy-specific RL training redistributes rather than removes bias, and language- and immigration-related cues produce larger gaps than gender- and SES-related cues.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.12949 [cs.AI]
(or
arXiv:2609.12949v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.12949
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiaxu Zhao [view email]
[v1]
Fri, 11 Sep 2026 15:10:07 UTC (1,435 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics, by Jiaxu Zhao and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)