Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens

2025-01-02

AI Summary

Contemporary educational AI systems leveraging large language models (e.g., GPT-4, Llama 3) exhibit significant cultural biases—particularly in representing non-Western traditions—exacerbating epistemic inequities and ethical risks. Method: Addressing the deficit in cultural inclusivity, this work formalizes “applied multiplexity”—a concept drawn from non-WEIRD wisdom traditions (e.g., Islamic epistemologies)—into an operationalizable AI auditing and governance paradigm. We propose two culturally balanced architectures: context-embedded and multi-agent collaborative. Within a multi-agent system (MAS) framework, we integrate culture-sensitive auditing, Perspective Distribution Scoring (PDS), cross-cultural sentiment analysis, and system-level prompt engineering to optimize Multiplex LLMs. Contribution/Results: Experiments demonstrate that PDS entropy increases from a baseline of 3.25% to 98%, markedly improving multicultural perspective balance and positive sentiment coverage across diverse cultural contexts.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

As large language models (LLMs) like GPT-4 and Llama 3 become integral to educational contexts, concerns are mounting over the cultural biases, power imbalances, and ethical limitations embedded within these technologies. Though generative AI tools aim to enhance learning experiences, they often reflect values rooted in Western, Educated, Industrialized, Rich, and Democratic (WEIRD) cultural paradigms, potentially sidelining diverse global perspectives. This paper proposes a framework to assess and mitigate cultural bias within LLMs through the lens of applied multiplexity. Multiplexity, inspired by Senturk et al. and rooted in Islamic and other wisdom traditions, emphasizes the coexistence of diverse cultural viewpoints, supporting a multi-layered epistemology that integrates both empirical sciences and normative values. Our analysis reveals that LLMs frequently exhibit cultural polarization, with biases appearing in both overt responses and subtle contextual cues. To address inherent biases and incorporate multiplexity in LLMs, we propose two strategies: extit{Contextually-Implemented Multiplex LLMs}, which embed multiplex principles directly into the system prompt, influencing LLM outputs at a foundational level and independent of individual prompts, and extit{Multi-Agent System (MAS)-Implemented Multiplex LLMs}, where multiple LLM agents, each representing distinct cultural viewpoints, collaboratively generate a balanced, synthesized response. Our findings demonstrate that as mitigation strategies evolve from contextual prompting to MAS-implementation, cultural inclusivity markedly improves, evidenced by a significant rise in the Perspectives Distribution Score (PDS) and a PDS Entropy increase from 3.25% at baseline to 98% with the MAS-Implemented Multiplex LLMs. Sentiment analysis further shows a shift towards positive sentiment across cultures,...

Problem

• Cultural Bias
• Educational Equity
• Power Imbalance

Innovation

• Multidimensionality
• Cultural Bias Reduction
• Perspective Distribution Score