Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Research Briefing
  • Published:

Generative AI predicts personality traits on the basis of open-ended narratives

Nature Human Behaviour (2026)Cite this article

Subjects

We show that widely available large language models (LLMs) can — out of the box — accurately score people’s personality traits on the basis of their brief, open-ended narratives. LLM ratings converged with self-reports, predicted daily behaviour and mental health, and outperformed traditional language processing methods. Thus, use of LLM tools emerges as an accurate, scalable and efficient approach to assessing arbitrary psychological constructs.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Correlations between LLM estimates of personality traits based on narrative text and self-reported traits.

References

  1. Modersitzki, N., Phan, L. V., McDonald, S., Wright, A. G. C. & Renner, K. H. Personality psychology is getting personal: advancing the field through personalization. Eur. J. Person. https://doi.org/10.1177/08902070251316915 (2025). This article reviews the rationale and challenges associated with developing a person-specific science of personality.

  2. Connelly, B. S. & Ones, D. S. An other perspective on personality: meta-analytic integration of observers’ accuracy and predictive validity. Psychol. Bull. 136, 1092–1122 (2010). This meta-analysis reports the agreement between self-rated personality traits and other-rated traits for many different types of other raters (for example, friends, family and co-workers).

    Article  PubMed  Google Scholar 

  3. John, O. P., Angleitner, A. & Ostendorf, F. The lexical approach to personality: a historical review of trait taxonomic research. Eur. J. Person. 2, 171–205 (1988). This review discusses the role the lexical hypotheses has had in establishing the most dominant models of personality, the Big Five and Five Factor Model.

    Article  Google Scholar 

  4. Roberts, B. W., Kuncel, N. R., Shiner, R., Caspi, A. & Goldberg, L. R. The power of personality: the comparative validity of personality traits, socioeconomic status, and cognitive ability for predicting important life outcomes. Perspect. Psychol. Sci. 2, 313–345 (2007). This review summarizes the predictive power of personality traits relative to other major predictors of life outcomes.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Wright, A. G. C. et al. Assessing personality using zero-shot generative AI scoring of brief open-ended text. Nat. Hum. Behav. https://doi.org/10.1038/s41562-025-02389-x (2026).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Generative AI predicts personality traits on the basis of open-ended narratives. Nat Hum Behav (2026). https://doi.org/10.1038/s41562-025-02397-x

Download citation

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41562-025-02397-x

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing