Large language models often stereotype older adults in stories

"Despite her age, Margaret was eager to make a change": Unpacking Aging Representations and Stereotypes in LLM-generated Stories

Human-Computer Interaction

Summary

Large language models (LLMs) create many everyday stories, but they tend to show younger characters most often and miss middle-aged adults. When older adults do appear, they are usually shown as losing abilities or needing help from younger people. Sometimes even positive stories make older adults’ successes seem surprising or have others decide things for them. The authors suggest looking not just at whether stories are positive or negative, but at who appears and who takes action, and involving older adults to get fairer portrayals.

What this means in practice

  • For ai writing tool developers: Create story generation tools that include more diverse and realistic portrayals of older adults with varied roles and decision-making power.
  • For content moderation teams: Identify and reduce ageist stereotypes in AI-generated stories to promote fairness and avoid reinforcing harmful biases.

Authors

MD. Roqunuzzaman Sojib, Mohammad Sadat Hossain, Nafis Tahmid, Shattik Islam Rhythm, Novia Nurain

Abstract

As large language models (LLMs) increasingly generate everyday stories, their portrayals can shape expectations about aging. Prior work has largely examined age stereotypes in short responses, leaving unanswered whose lives models default to imagining and how age shapes characters' roles in complete narratives. We analyze 594 stories generated by Gemini, GPT, and Llama using text embeddings, LLM-assisted coding, and qualitative analysis. When age was unspecified, stories typically featured younger adults, with middle-aged protagonists largely absent. Older adults were often portrayed through loss, familiar routines, and help from younger characters. Even positive stories sometimes treated older adults' achievements as surprising or portrayed others making decisions on their behalf. We suggest evaluating not only the tone of generated stories, but also who appears, what opportunities they receive, and who makes decisions. Involving older adults in these evaluations can guide writing tools toward more varied, less stereotyped portrayals of later life.