The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students

• URL: http://arxiv.org/abs/2607.11292v1
• Date: Mon, 13 Jul 2026 09:10:19 GMT
• Title: The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students
• Abstract summary: This study presents a systematic API audit of four Large Language Models acting as history tutors, evaluating 1,800 responses regarding the 1989 Romanian Revolution.<n>We uncover four interconnected patterns of emphepistemic paternalism<n>We argue that current safety alignment acts as a paternalistic filter, transforming conversational AI into agents of narrative segregation.
• Score: 0.15293427903448023
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics [7.575642125191585]
  Large language models (LLMs) are increasingly deployed as tutors, but it is unclear whether they support all students equally well.<n>We introduce textbfEduFair-Bench, a benchmark for auditing the pedagogical fairness of LLM tutors.
  arXiv  Detail & Related papers  (2026-09-11T15:10:07Z)
• Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients [13.60111351173797]
  LLM-governed social robots increasingly decide who receives real-world assistance first.<n>As prioritization norms vary across cultures by age, status, and group size, failure to calibrate pluralistically can scale into unequal access.<n>We introduce a gradient-based audit framework for multilingual evaluation of LLM moral trade-off behavior.
  arXiv  Detail & Related papers  (2026-06-02T10:22:53Z)
• Faster Completion, Less Learning: Generative AI Reduced Study Time on Math Problems and the Knowledge They Build [0.6524460254566904]
  Self-report surveys show little change, while small-scale behavioral studies report widespread AI use without the scale or duration to measure learning consequences.<n>We use a ten-year panel of $3.2$ million ALEKS learning interactions for the time-on-task analysis.<n>These results are among the first large-scale behavioral and outcome evidence that generative AI has altered how students study and the knowledge they build.
  arXiv  Detail & Related papers  (2026-05-20T18:40:53Z)
• Sociodemographic Biases in Educational Counselling by Large Language Models [61.30199414932204]
  This study examines sociodemographic biases in Large Language Models (LLMs)<n>We evaluate responses from six LLMs answering questions about 900 vignettes describing students in diverse circumstances.
  arXiv  Detail & Related papers  (2026-04-03T14:08:22Z)
• Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum [0.0]
  The integration of Large Language Models into educational ecosystems promises to democratize access to personalized tutoring.<n>This study presents a systematic evaluation of four state-of-the-art LLMs--GPT-4o, Claude Sonnet 4, Qwen3-235B, and Kimi K2--assessing their capacity to function as AI tutors.
  arXiv  Detail & Related papers  (2026-03-17T04:37:22Z)
• Language, Caste, and Context: Demographic Disparities in AI-Generated Explanations Across Indian and American STEM Educational Systems [2.0722928522838693]
  This paper asks how do LLMs perceive the intellectual capabilities of student profiles from intersecting marginalized identities across different cultural contexts?<n>We construct profiles combining caste, medium of instruction, and school boards in India, and race, HBCU attendance, and school type in America, alongside universal factors like income and college tier.<n>We observe biases providing lower-quality outputs to profiles with marginalized backgrounds in both contexts.
  arXiv  Detail & Related papers  (2026-01-20T21:58:45Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes [1.7188280334580197]
  We present the first study to evaluate large language models (LLMs) using a validated social science instrument designed to measure human response to everyday conflict.<n>To assess potential bias, we introduce persona-based prompting that varies race, age, and geographic identity within the United States.<n>Our study reveals two key findings: (1) LLMs surface-level text generation often diverges from their internal preference for violent responses; (2) their violent tendencies vary across demographics, frequently contradicting established findings in criminology, social science, and psychology.
  arXiv  Detail & Related papers  (2025-06-25T20:43:04Z)
• Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach [53.824673312331626]
  Implicit Demography Inference (IDI) module uses k-means clustering to mitigate bias in Speech Emotion Recognition (SER)<n>Experiments show that pseudo-labeling IDI reduces subgroup disparities, improving fairness metrics by over 28%.<n>Unsupervised IDI yields more than a 4.6% improvement in fairness metrics with a drop of less than 3.6% in SER performance.
  arXiv  Detail & Related papers  (2025-05-20T14:50:44Z)
• Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students [53.20318273452059]
  Large language models (LLMs) like OpenAI's ChatGPT have opened up new avenues in education.<n>Despite school restrictions, our survey of over 300 middle and high school students revealed that a remarkable 70% of students have utilized LLMs.<n>We propose a few ideas to address such issues, including subject-specific models, personalized learning, and AI classrooms.
  arXiv  Detail & Related papers  (2024-11-27T19:19:34Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs [58.27353205269664]
  Social biases can manifest in language agency in Large Language Model (LLM)-generated content.<n>We introduce the Language Agency Bias Evaluation benchmark, which comprehensively evaluates biases in LLMs.<n>Using LABE, we unveil language agency social biases in 3 recent LLMs: ChatGPT, Llama3, and Mistral.
  arXiv  Detail & Related papers  (2024-04-16T12:27:54Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.