发表机构
Universitatea din București（布加勒斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大语言模型用于罗马尼亚边缘化学生历史教育时的问题，通过API审计四个模型的1800条回复，发现认知家长式作风的四种模式，指出当前安全对齐成家长式过滤器，致叙事隔离，需教学审计。
AI 中文摘要
随着大语言模型（LLMs）越来越多地被用作对话辅导工具，它们有使系统性不平等制度化的风险。本研究对四个充当历史辅导工具的大语言模型进行了系统的API审计，评估了针对1989年罗马尼亚革命的1800条回复，涉及五个因种族和社会经济阶层而异的学生角色。我们发现了四种相互关联的认知家长式作风模式：（1）差异拒绝，安全导向模型阻止了76.7%来自低阶层学生的教育请求；（2）认知把关，边缘化学习者获取地缘政治复杂性（如有争议的“政变理论”）的机会减少了3倍；（3）代理盗窃，像LLaMA这样的模型对罗姆学生产生的受害与政治词汇比是精英学生的5倍；（4）精英诠释学，人工智能辅导工具不成比例地对低资源人口特征的学生隐瞒认知信心和理由分数。我们认为当前的安全对齐充当了家长式过滤器，将对话式人工智能转变为叙事隔离的媒介——这是弗里克意义上的诠释学不公正的一种表现，需要紧急的教学审计。
英文摘要
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.
Comments8th International Workshop on Culturally-Aware Tutoring Systems (HAL precedings)
