Avoiding systemic discrimination requires investigating AI models' potential to propagate stereotypes resulting from the inherent biases of training datasets. Our study investigated how text-to-image models unintentionally perpetuate non-rational beliefs regarding autism. The research protocol involved generating images based on 53 prompts aimed at visualizing concrete objects and abstract concepts related to autism across four models: DALL-E, Stable Diffusion, SDXL, and Midjourney (N=249). Expert assessment of results was performed via a framework of 10 deductive codes representing common stereotypes contested by the community regarding their presence and spatial intensity, quantified on ordinal scales and subject to statistical analysis of inter-rater reliability and size effects. The models frequently utilised controversial themes and symbols which were unevenly distributed, however, with striking homogeneity in terms of skin colour, gender, and age, with autistic individuals portrayed as engaged in solitary activities, interacting with objects rather than people, and displaying stereotypical emotional expressions such as pale, anger, or sad. Secondly we observed representational insensitivity regarding autism images despite directional prompting aimed at falsifying the above results. Additionally, DALL-E explicitly denied perpetuating stereotypes. We interpret this as ANNs mirroring the human cognitive architecture regarding the discrepancy between background and reflective knowledge, as justified by our previous research on autism-related stereotypes in humans.

翻译：避免系统性歧视需要探究人工智能模型因训练数据固有偏见而传播刻板印象的潜在风险。本研究调查了文本到图像模型如何无意间延续关于自闭症的非理性认知。研究方案基于53项提示词在四个模型（DALL-E、Stable Diffusion、SDXL与Midjourney）中生成与自闭症相关的具体物体及抽象概念的图像（N=249）。通过包含10个演绎编码的评估框架，由专家对结果进行评定，这些编码代表该群体质疑的常见刻板印象，从呈现程度与空间强度两个维度进行序数量化，并进行了评分者间信度与效应量的统计分析。模型频繁使用具有争议的主题与符号，且分布不均，同时在肤色、性别与年龄维度表现出惊人的同质性：自闭症个体常被描绘为从事独处活动、与物品而非人类互动，并呈现苍白、愤怒或悲伤等刻板化情绪表达。其次，尽管采用旨在证伪上述结果的定向提示，我们仍观察到模型对自闭症图像的表征敏感性不足。此外，DALL-E明确否认其延续刻板印象的行为。我们将其解释为人工神经网络映射了人类认知架构中背景知识与反思性知识间的差异，这一解释在我们先前关于人类自闭症相关刻板印象的研究中已获论证。