Standard

Automated Assessment of Creativity in Multilingual Narratives. / Luchini, S.A.; Moosa, I.M.; Patterson, J.D.; Johnson, D.; Baas, M.; Barbot, B.; Bashmakova, I.; Benedek, M.; Chen, Q.; Corazza, G.E.; Forthmann, B.; Goecke, B.; Said-Metwaly, S.; Karwowski, M.; Kenett, Y.N.; Lebuda, I.; Lubart, T.; Miroshnik, K.G.; Obialo, F.-K.; Ovando-Tellez, M.; Primi, R.; Puente-Díaz, R.; Stevenson, C.; Volle, E.; Zielińska, A.; Van Hell, J.G.; Yin, W.; Beaty, R.E.

в: Psychology of Aesthetics, Creativity, and the Arts, 2025.

Результаты исследований: Научные публикации в периодических изданияхстатьяРецензирование

Harvard

Luchini, SA, Moosa, IM, Patterson, JD, Johnson, D, Baas, M, Barbot, B, Bashmakova, I, Benedek, M, Chen, Q, Corazza, GE, Forthmann, B, Goecke, B, Said-Metwaly, S, Karwowski, M, Kenett, YN, Lebuda, I, Lubart, T, Miroshnik, KG, Obialo, F-K, Ovando-Tellez, M, Primi, R, Puente-Díaz, R, Stevenson, C, Volle, E, Zielińska, A, Van Hell, JG, Yin, W & Beaty, RE 2025, 'Automated Assessment of Creativity in Multilingual Narratives', Psychology of Aesthetics, Creativity, and the Arts. https://doi.org/10.1037/aca0000725

APA

Luchini, S. A., Moosa, I. M., Patterson, J. D., Johnson, D., Baas, M., Barbot, B., Bashmakova, I., Benedek, M., Chen, Q., Corazza, G. E., Forthmann, B., Goecke, B., Said-Metwaly, S., Karwowski, M., Kenett, Y. N., Lebuda, I., Lubart, T., Miroshnik, K. G., Obialo, F-K., ... Beaty, R. E. (2025). Automated Assessment of Creativity in Multilingual Narratives. Psychology of Aesthetics, Creativity, and the Arts. https://doi.org/10.1037/aca0000725

Vancouver

Luchini SA, Moosa IM, Patterson JD, Johnson D, Baas M, Barbot B и пр. Automated Assessment of Creativity in Multilingual Narratives. Psychology of Aesthetics, Creativity, and the Arts. 2025. https://doi.org/10.1037/aca0000725

Author

Luchini, S.A. ; Moosa, I.M. ; Patterson, J.D. ; Johnson, D. ; Baas, M. ; Barbot, B. ; Bashmakova, I. ; Benedek, M. ; Chen, Q. ; Corazza, G.E. ; Forthmann, B. ; Goecke, B. ; Said-Metwaly, S. ; Karwowski, M. ; Kenett, Y.N. ; Lebuda, I. ; Lubart, T. ; Miroshnik, K.G. ; Obialo, F.-K. ; Ovando-Tellez, M. ; Primi, R. ; Puente-Díaz, R. ; Stevenson, C. ; Volle, E. ; Zielińska, A. ; Van Hell, J.G. ; Yin, W. ; Beaty, R.E. / Automated Assessment of Creativity in Multilingual Narratives. в: Psychology of Aesthetics, Creativity, and the Arts. 2025.

BibTeX

@article{f81d5c5a323243858b83ce7242fcc8a9,
title = "Automated Assessment of Creativity in Multilingual Narratives",
abstract = "Researchers and educators interested in creative writing need a reliable and efficient tool to score the creativity of narratives, such as short stories. Typically, human raters manually assess narrative creativity, but such subjective scoring is limited by labor costs and rater disagreement. Large language models (LLMs) have shown remarkable success on creativity tasks, yet they have not been applied to scoring narratives, including multilingual stories. In the present study, we aimed to test whether narrative originality—a component of creativity— could be automatically scored by LLMs, further evaluating whether a single LLM could predict human originality ratings across multiple languages.We trained three different LLMs to predict the originality of short stories written in 11 languages. Our first monolingual model, trained only on English stories, robustly predicted human originality ratings (r=.81). This same model—trained and tested on multilingual stories translated into English—strongly predicted originality ratings of multilingual narratives (r≥.73). Finally, a multilingual model trained on the same stories, in their original language, reliably predicted human originality scores across all languages (r ≥.72).We thus demonstrate that LLMs can successfully score narrative creativity in 11 different languages, surpassing the performance of the best previous automated scoring techniques (e.g., semantic distance). This work represents the first effective, accessible, and reliable solution for the automated scoring of creativity in multilingual narratives. {\textcopyright} 2025 Elsevier B.V., All rights reserved.",
keywords = "automated scoring, creative writing, creativity assessment, large language models, narratives",
author = "S.A. Luchini and I.M. Moosa and J.D. Patterson and D. Johnson and M. Baas and B. Barbot and I. Bashmakova and M. Benedek and Q. Chen and G.E. Corazza and B. Forthmann and B. Goecke and S. Said-Metwaly and M. Karwowski and Y.N. Kenett and I. Lebuda and T. Lubart and K.G. Miroshnik and F.-K. Obialo and M. Ovando-Tellez and R. Primi and R. Puente-D{\'i}az and C. Stevenson and E. Volle and A. Zieli{\'n}ska and {Van Hell}, J.G. and W. Yin and R.E. Beaty",
note = "Export Date: 01 November 2025; Cited By: 6; Correspondence Address: S.A. Luchini; Department of Psychology, Pennsylvania State University, United States; email: skl5875@psu.edu; R.E. Beaty; Department of Psychology, Pennsylvania State University, United States; email: rebeaty@psu.edu",
year = "2025",
doi = "10.1037/aca0000725",
language = "English",
journal = "Psychology of Aesthetics, Creativity, and the Arts",
issn = "1931-3896",
publisher = "American Psychological Association",

}

RIS

TY - JOUR

T1 - Automated Assessment of Creativity in Multilingual Narratives

AU - Luchini, S.A.

AU - Moosa, I.M.

AU - Patterson, J.D.

AU - Johnson, D.

AU - Baas, M.

AU - Barbot, B.

AU - Bashmakova, I.

AU - Benedek, M.

AU - Chen, Q.

AU - Corazza, G.E.

AU - Forthmann, B.

AU - Goecke, B.

AU - Said-Metwaly, S.

AU - Karwowski, M.

AU - Kenett, Y.N.

AU - Lebuda, I.

AU - Lubart, T.

AU - Miroshnik, K.G.

AU - Obialo, F.-K.

AU - Ovando-Tellez, M.

AU - Primi, R.

AU - Puente-Díaz, R.

AU - Stevenson, C.

AU - Volle, E.

AU - Zielińska, A.

AU - Van Hell, J.G.

AU - Yin, W.

AU - Beaty, R.E.

N1 - Export Date: 01 November 2025; Cited By: 6; Correspondence Address: S.A. Luchini; Department of Psychology, Pennsylvania State University, United States; email: skl5875@psu.edu; R.E. Beaty; Department of Psychology, Pennsylvania State University, United States; email: rebeaty@psu.edu

PY - 2025

Y1 - 2025

N2 - Researchers and educators interested in creative writing need a reliable and efficient tool to score the creativity of narratives, such as short stories. Typically, human raters manually assess narrative creativity, but such subjective scoring is limited by labor costs and rater disagreement. Large language models (LLMs) have shown remarkable success on creativity tasks, yet they have not been applied to scoring narratives, including multilingual stories. In the present study, we aimed to test whether narrative originality—a component of creativity— could be automatically scored by LLMs, further evaluating whether a single LLM could predict human originality ratings across multiple languages.We trained three different LLMs to predict the originality of short stories written in 11 languages. Our first monolingual model, trained only on English stories, robustly predicted human originality ratings (r=.81). This same model—trained and tested on multilingual stories translated into English—strongly predicted originality ratings of multilingual narratives (r≥.73). Finally, a multilingual model trained on the same stories, in their original language, reliably predicted human originality scores across all languages (r ≥.72).We thus demonstrate that LLMs can successfully score narrative creativity in 11 different languages, surpassing the performance of the best previous automated scoring techniques (e.g., semantic distance). This work represents the first effective, accessible, and reliable solution for the automated scoring of creativity in multilingual narratives. © 2025 Elsevier B.V., All rights reserved.

AB - Researchers and educators interested in creative writing need a reliable and efficient tool to score the creativity of narratives, such as short stories. Typically, human raters manually assess narrative creativity, but such subjective scoring is limited by labor costs and rater disagreement. Large language models (LLMs) have shown remarkable success on creativity tasks, yet they have not been applied to scoring narratives, including multilingual stories. In the present study, we aimed to test whether narrative originality—a component of creativity— could be automatically scored by LLMs, further evaluating whether a single LLM could predict human originality ratings across multiple languages.We trained three different LLMs to predict the originality of short stories written in 11 languages. Our first monolingual model, trained only on English stories, robustly predicted human originality ratings (r=.81). This same model—trained and tested on multilingual stories translated into English—strongly predicted originality ratings of multilingual narratives (r≥.73). Finally, a multilingual model trained on the same stories, in their original language, reliably predicted human originality scores across all languages (r ≥.72).We thus demonstrate that LLMs can successfully score narrative creativity in 11 different languages, surpassing the performance of the best previous automated scoring techniques (e.g., semantic distance). This work represents the first effective, accessible, and reliable solution for the automated scoring of creativity in multilingual narratives. © 2025 Elsevier B.V., All rights reserved.

KW - automated scoring

KW - creative writing

KW - creativity assessment

KW - large language models

KW - narratives

UR - https://www.mendeley.com/catalogue/fbfef7b1-5998-3136-bea5-1025907981b4/

U2 - 10.1037/aca0000725

DO - 10.1037/aca0000725

M3 - Article

JO - Psychology of Aesthetics, Creativity, and the Arts

JF - Psychology of Aesthetics, Creativity, and the Arts

SN - 1931-3896

ER -

ID: 143614000