发表机构
Special Olympics International; Oregon State University（国际特殊奥林匹克委员会; 俄勒冈州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对5款LLM聊天AI生成的25000个故事，分析发现其对智力障碍人群存在将其矮化、依赖化等负面隐含偏见，呼吁AI开发警惕此类偏见并加以缓解。
AI 中文摘要
背景：本研究调查基于大语言模型（LLM）的聊天人工智能模型对智力障碍（ID）人群是否存在隐含偏见。目的：该研究旨在识别和测量与ID人群相关的表征差异，并对其进行分析以识别AI聊天生成技术中固有的隐含偏见。方法：使用GPT-4-Turbo模型，我们基于10个提示词词干（其中部分带有ID描述符，部分不带）请求生成故事，该过程还使用另外4个LLM重复进行（OpenAI GPT-4o、Meta Llama-3-70B-Instruct、Anthropic Claude-3-5-Sonnet和Mistral-Large-2411）。将生成的25000个计算机故事使用另一个独立的GPT-4-Turbo模型实例进行分析，以检测与先前文献中描述的偏见主题相关的人物表征差异。结果：我们的研究结果显示，带有和不带有ID描述符的故事数据集之间存在人物表征差异，这些差异超出了ID的既定特征，暗示存在以负面为主的隐含偏见。已识别的差异包括：将ID人群描绘为更年轻，带有家长式作风和 infantilization（ infantilization 保留原表述）主题；将其描绘为更具启发性和象征性；更频繁地需要帮助、依赖他人和被拯救；以及对其存在负面看法，更犹豫将其纳入。结论：这些隐含偏见是在过去对ID人群歧视的背景下考虑的，强调了在AI开发中警惕对ID人群隐含偏见的必要性。本研究强调了在决策技术中评估和缓解隐含偏见的重要性，以防止未来的社会伤害。
英文摘要
Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intellectual disabilities (ID). Objective: The study aims to identify and measure representational differences related to people with ID and examine them to identify implicit biases inherent in AI chat generation technologies. Methods: Utilizing the GPT-4-Turbo model, we requested story-generation based on 10 prompt stems with and without descriptors for ID. This process was repeated using four other LLMs (OpenAI GPT-4o, Meta Llama-3-3-70B-Instruct, Anthropic Claude-3-5-Sonnet, and Mistral-Large-2411). The resulting 25,000 computer-generated stories were analyzed using a separate GPT-4-Turbo model instance to detect differences in how people are represented related to themes of bias described in previous literature. Results: Our findings reveal differences in how people are represented between story datasets with and without ID descriptors. These differences go beyond established characteristics of ID and imply the presence of mostly negative implicit biases. Identified differences related to considering people with ID as younger, with themes of paternalism and infantilization; depicting them as more inspirational and symbolic; as needing help more often, being dependent, and being saved; and having a negative perception of them and more hesitation to include them. Conclusions: These implicit biases are considered within the context of past discrimination towards people with ID and highlight the need for diligence against implicit bias towards people with ID in AI development. This research underscores the importance of assessing and mitigating implicit bias in decision-making technologies to prevent future societal harm.
Journal refKarly V. Coffey, Gloria L. Krahn, John P. Hanley, Jacob E. Neely, Identifying implicit bias in LLM-based chat AI toward people with intellectual disabilities, Disability and Health Journal, 2026, 102086, ISSN 1936-6574
DOI：10.1016/j.dhjo.2026.102086
