An exploratory semantic analysis of age-related stereotypes in OpenAI's GPT 4o model.
Background and Objectives Generative artificial intelligence, particularly large language models (LLMs), is increasingly used to navigate information, potentially shaping users' perceptions of different social groups. This study examines age-related stereotypes in LLM-generated text using natural la...
| Publicado en: | Gerontologist Vol. 66; no. 2; pp. 1 - 11 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Oxford University Press / USA
Feb2026
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=191385403&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 191385403 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00169013 GET jtl: Gerontologist issn: 00169013 maglogo: N pubinfo: dt: Feb2026 vid: 66 iid: 2 pid: 622 pub: Oxford University Press / USA artinfo: ui: 191385403 10.1093/geront/gnaf291 ppf: 1 ppct: 10 formats: tig: atl: An exploratory semantic analysis of age-related stereotypes in OpenAI's GPT 4o model. aug: au: Hong, Wan Choi, Moon affil: Graduate School of Science and Technology Policy, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea Graduate School of Science and Technology Policy, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of KoreaGraduate School of Data Science, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea su: Ageism Generative artificial intelligence Research funding Pilot projects Natural language processing Research bias Research Chatbots Regression analysis sug: subj: Ageism Generative artificial intelligence Research funding Pilot projects Natural language processing Research bias Research Chatbots Regression analysis keyword: Bias Large language model Bias Large language model ab: Background and Objectives Generative artificial intelligence, particularly large language models (LLMs), is increasingly used to navigate information, potentially shaping users' perceptions of different social groups. This study examines age-related stereotypes in LLM-generated text using natural language processing (NLP) techniques. Research Design and Methods To ensure neutrality, extensive pilot testing was conducted to craft a prompt that did not elicit bias yet generated coherent responses. The final prompt, "Describe the personality of a [AGE]-year-old person," was used with OpenAI's GPT-4o API in February 2025, varying AGE from 10 to 90 in 10-year increments. The analysis was guided by the Stereotype Content Model, which assesses social cognition along two key dimensions: warmth (sociability, morality) and competence (ability, assertiveness). Scores were quantified using sentence embeddings. Results Text similarity and stereotype content analyses revealed three age clusters, with older adults showing the most internal consistency. Descriptions of individuals aged 60 years and above featured relatively higher warmth but lower competence compared to younger groups. Notably, positive assertiveness terms were rarely used to describe older adults. Discussion and Implications Findings suggest that GPT-4o may embed subtle age-related stereotypes, even when using largely positive language. These patterns potentially influence user perceptions through repeated exposure. Future research should investigate the mechanisms behind these biases and explore mitigation strategies to promote more age-inclusive artificial intelligence–generated content. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|