Study finds AI-generated animal stories rarely have a female lead
A new University of Washington study found that when AI models write stories about talking animals, the lead character is rarely ever female.
A recent study reveals that artificial intelligence-generated animal stories seldom feature a female protagonist. Melanie Walsh, an assistant professor at the University of Washington's Information School, led the research, which examined how six popular AI models approach storytelling based on animal characters. The team fed each AI model the same prompt and analyzed the resulting stories.
Out of 23,800 completions, only 513 contained a female lead, equating to roughly one in every 46 stories. Neutral characters accounted for 57 percent, while male characters made up 41 percent of the narratives. Walsh speculates that AI companies use neutral pronouns to avoid gender bias, which inadvertently excludes female characters altogether.
Among the tested models, GPT-5.1 and Gemini 2.5 produced the most stories with male leads, at 65 percent and 63 percent, respectively. OLMo 3 favored neutral characters, with 85 percent of its stories lacking a gendered lead. Claude Sonnet 4.5 generated female characters in just under 4 percent of its responses, the highest percentage among the models tested.
These findings highlight the pervasive bias in AI systems, similar to other research showing that chatbot decisions can be influenced by traits such as age, religion, and gender.
Written by urgent.news from Digital Trends's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
