Understanding Down Syndrome Stereotypes in LLM-Based Personas

2025-12-01

AI Summary

This study addresses the risk of stereotyping and oversimplification when constructing personas for individuals with Down syndrome in the Persona-L system—built upon large language models (LLMs) and retrieval-augmented generation (RAG). We propose the first participatory persona modeling framework integrating stereotype detection. Through LLM-generated content analysis, RAG-enhanced factual consistency verification, and multi-round qualitative interviews with individuals with Down syndrome and their caregivers, we systematically identify three bias sources: training data skew, interface interaction design flaws, and inappropriate LLM tone. Our contributions are threefold: (1) the first integration of stereotype detection into the persona modeling pipeline; (2) adoption of participatory methods to ensure authentic, diverse, and person-centered representation; and (3) development of actionable, healthcare-humanities–informed bias mitigation strategies. The results provide a reusable methodology and empirical foundation for designing inclusive, AI-driven human-computer interaction systems.

Technology Category

• Humans and AI: AI for Accessibility
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

We present a case study of Persona-L, a system that leverages large language models (LLMs) and retrieval-augmented generation (RAG) to model personas of people with Down syndrome. Existing approaches to persona creation can often lead to oversimplified or stereotypical profiles of people with Down Syndrome. To that end, we built stereotype detection capabilities into Persona-L. Through interviews with caregivers and healthcare professionals (N=10), we examine how Down Syndrome stereotypes could manifest in both, content and delivery of LLMs, and interface design. Our findings show the challenges in stereotypes definition, and reveal the potential stereotype emergence from the training data, interface design, and the tone of LLM output. This highlights the need for participatory methods that capture the heterogeneity of lived experiences of people with Down Syndrome.

Problem

• Detects stereotypes in LLM personas for Down syndrome
• Examines stereotype sources in content, delivery, and interface design
• Advocates participatory methods for diverse lived experiences

Innovation

• LLM and RAG for Down Syndrome persona modeling
• Stereotype detection integrated into persona system
• Participatory methods to capture lived experience diversity