Biased Tales: Cultural and Topic Bias in Generating Children's Stories
This addresses biases in AI-generated content for children, which is an incremental step toward more equitable creative AI use.
The study tackled the problem of cultural and gender biases in large language model-generated children's stories, finding that stories with girl protagonists had a 55.26% increase in appearance-related attributes and those for non-Western children overemphasized cultural themes.
Stories play a pivotal role in human communication, shaping beliefs and morals, particularly in children. As parents increasingly rely on large language models (LLMs) to craft bedtime stories, the presence of cultural and gender stereotypes in these narratives raises significant concerns. To address this issue, we present Biased Tales, a comprehensive dataset designed to analyze how biases influence protagonists' attributes and story elements in LLM-generated stories. Our analysis uncovers striking disparities. When the protagonist is described as a girl (as compared to a boy), appearance-related attributes increase by 55.26%. Stories featuring non-Western children disproportionately emphasize cultural heritage, tradition, and family themes far more than those for Western children. Our findings highlight the role of sociocultural bias in making creative AI use more equitable and diverse.