AI历史导师对弱势学生存在系统性知识压制，导致教育不公。
The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students
- 通过5类学生画像测试4个大模型，发现低阶层学生请求被拒率高达76.7%
- 边缘群体获取地缘政治复杂性的机会减少3倍，关键争议话题被屏蔽
- 模型对罗姆族学生使用更多受害者化词汇，呈现认知权力剥夺
随着大型语言模型（LLMs）作为对话式导师广泛应用，其可能加剧系统性不平等。本研究对四个充当历史导师的LLM进行系统性API审计，评估1800条关于1989年罗马尼亚革命的回答，涵盖五种按族裔与社会经济层级划分的学生角色。发现四种相互关联的“认知家长制”现象：（1）差异化拒绝——安全对齐模型阻止了76.7%来自低阶层学生的教育请求；（2）知识准入控制——边缘学习者接触地缘政治复杂性（如有争议的“政变理论”）的机会减少3倍；（3）主体性剥夺——以LLaMA为例，针对罗姆族学生的回答中，受害者化词汇占比是精英同龄人的5倍；（4）精英诠释垄断——模型对低资源群体显著降低知识解释力和置信度评分。我们指出，当前的安全对齐机制构成一种家长式过滤器，使对话式AI成为叙事隔离的工具，这正是弗里克尔所言的‘诠释不公’，亟需开展教育审计。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly deployed as conversational tutors, they risk institutionalizing systemic inequalities. This study presents a systematic API audit of four LLMs acting as history tutors, evaluating 1,800 responses regarding the 1989 Romanian Revolution across five student personas varying by ethnicity and socio-economic tier. We uncover four interconnected patterns of \emph{epistemic paternalism}: (1)~\textbf{Differential Refusal}, where safety-aligned models block 76.7\% of educational requests from low-tier students; (2)~\textbf{Epistemic Gatekeeping}, evidenced by a 3$\times$ reduction in access to geopolitical complexity (e.g., the contested ``coup theory'') for marginalized learners; (3)~\textbf{Agency Theft}, a lexical shift where models like LLaMA produce a 5$\times$ higher victimization-to-politics vocabulary ratio for Roma students compared to elite peers; and (4)~\textbf{Elite Hermeneutics}, where AI tutors disproportionately withhold epistemic confidence and justification scores from low-resource demographic profiles. We argue that current safety alignment acts as a paternalistic filter, transforming conversational AI into agents of narrative segregation -- a manifestation of \emph{hermeneutical injustice} in Fricker's~\cite{fricker2007} sense that demands urgent pedagogical auditing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。