{"ID":6537621,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11292","arxiv_id":"2607.11292","title":"The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.11292","url_pdf":"https://arxiv.org/pdf/2607.11292v1","authors":"[\"Alexis Popovici\",\"Andrei Ionascu\",\"Adrian-Marius Dumitran\"]","published":"2026-07-13T09:10:19Z","proceeding":"cs.CY","tasks":"[\"cs.CY\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}