Assessing novelty, feasibility and value of creative ideas with an unsupervised approach using GPT‐4.
Creativity is defined by three key factors: novelty, feasibility and value. While many creativity tests focus primarily on novelty, they often neglect feasibility and value, thereby limiting their reflection of real‐world creativity. In this study, we employ GPT‐4, a large language model, to assess...
| Publicado en: | British Journal of Psychology Vol. 117; no. 2; pp. 741 - 761 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Wiley-Blackwell
May2026
|
| 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=192785878&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 192785878 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00071269 BJP jtl: British Journal of Psychology issn: 00071269 maglogo: Y pubinfo: dt: May2026 vid: 117 iid: 2 pid: 480 pub: Wiley-Blackwell artinfo: ui: 192785878 10.1111/bjop.12720 ppf: 741 ppct: 20 formats: fmt: – @attributes: type: T – @attributes: type: C – @attributes: type: P size: 1008KB tig: atl: Assessing novelty, feasibility and value of creative ideas with an unsupervised approach using GPT‐4. aug: au: Kern, Felix B. Wu, Chien‐Te Chao, Zenas C. affil: International Research Center for Neurointelligence (WPI‐IRCN), UTIAS, The University of Tokyo, Tokyo, Japan su: Japan Problem solving Creative ability Psychological tests Judgment (Psychology) Generative artificial intelligence Scale analysis (Psychology) Pearson correlation (Statistics) Research funding Data analysis Descriptive statistics Statistics Algorithms sug: subj: Problem solving Creative ability Psychological tests Judgment (Psychology) Japan Generative artificial intelligence Scale analysis (Psychology) Pearson correlation (Statistics) Research funding Data analysis Descriptive statistics Statistics Algorithms keyword: AUT creativity large language models AUT creativity large language models ab: Creativity is defined by three key factors: novelty, feasibility and value. While many creativity tests focus primarily on novelty, they often neglect feasibility and value, thereby limiting their reflection of real‐world creativity. In this study, we employ GPT‐4, a large language model, to assess these three dimensions in a Japanese‐language Alternative Uses Test (AUT). Using a crowdsourced evaluation method, we acquire ground truth data for 30 question items and test various GPT prompt designs. Our findings show that asking for multiple responses in a single prompt, using an 'explain first, rate later' design, is both cost‐effective and accurate (r =.62,.59 and.33 for novelty, feasibility and value, respectively). Moreover, our method offers comparable accuracy to existing methods in assessing novelty, without the need for training data. We also evaluate additional models such as GPT‐4 Turbo, GPT‐4 Omni and Claude 3.5 Sonnet. Comparable performance across these models demonstrates the universal applicability of our prompt design. Our results contribute a straightforward platform for instant AUT evaluation and provide valuable ground truth data for future methodological research. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|