发现大模型对智力障碍者存在隐性偏见，表现为过度保护与刻板印象。
Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities
- 用10个提示词对比生成带/不带智力障碍描述的故事
- 25,000条故事显示智力障碍者被刻画得更年轻、需被拯救、依赖性强
- 揭示模型隐含偏见，提醒开发者警惕技术对弱势群体的伤害
本研究调查基于大型语言模型（LLM）的聊天AI对智力障碍（ID）人群是否存在隐性偏见。通过GPT-4-Turbo等五款模型，分别针对10个提示词生成带有和不带智力障碍描述的故事，共获得25,000条文本。使用另一GPT-4-Turbo实例分析其表现差异，发现模型在描绘智力障碍者时存在显著偏差：表现为将其视为更年轻、更需保护、更易被救赎，强调其励志象征意义，同时减少对其独立性的认可，增加回避或犹豫。这些偏差超越了智力障碍本身的特征，体现出普遍的父权式关怀与去人性化倾向。研究指出，此类隐性偏见与历史上对智力障碍者的歧视一脉相承，警示在人工智能开发中必须主动识别并缓解此类偏见，以避免对社会造成潜在伤害。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。