Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Claire E. Stevenson has a total of 166 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Automated assessment of creativity in multilingual narratives.

    by Simone A. Luchini, Ibraheem Muhammad Moosa, John D. Patterson, Dan Johnson, Matthijs Baas, Baptiste Barbot, Iana Bashmakova, Mathias Benedek, Qunlin Chen, Giovanni E. Corazza, et al.


  • Open Access

    Collaborative Creative Story Generation with Peers vs Chatbots: A Pilot Study

    by Leyla Yang, Janet Rafner, Claire Stevenson

    Does partnering with an AI chatbot genuinely enhance creativity, or does it simply create the illusion of creativity through more complex language? Prior work suggests that human–AI collaboration can increase creativity scores, but that this advantage often disappears once verbosity (i.e., word count) is controlled for. In contrast, human–human collaboration tends to yield more diverse and original ideas. However, existing research on co-creativity is fragmented in its measurement approaches and largely concentrates on final outputs rather than the collaborative process. To address this gap, we examined co-creative short story writing using objective metrics and process analyses, comparing three conditions: human-human collaboration (n=57), human-AI collaboration (n=57), and AI-alone (n=69). Our results showed that two collaborating humans were more creative than the human-AI pairs. When analyzing the co-creative process in human-AI pairs, we saw a significant portion of people outsourcing the task to the chatbot. However, the more the human collaborated with the chatbot and synthesized their ideas into the chatbot-generated story, the more creative the human-AI product was.

  • Creative Cognition: A Collaborative Research Agenda

    by Wendy Ross, Sergio Agnoli, Matthijs Baas, Amory H. Danek, Izabela Lebuda, Rakefet Ackerman, Artur Ammalainen, Mathias Benedek, Honghong Bai, Linden J. Ball, et al.

    Creative cognition research has flourished in recent decades, revealing how extraordinary creative outcomes emerge from ordinary cognitive processes. However, the field faces fragmentation that hinders consensus and integration. This research agenda, developed through a collaborative workshop of 50 European researchers at the Lorentz Centre in Leiden, the Netherlands, identifies four critical challenges for advancing creative cognition research. Challenge 1 addresses theoretical concerns around defining core research terms like divergent thinking, emotions, and metacognition. Challenge 2 focuses on identifying different types and domains of knowledge that influence creative performance. Challenge 3 emphasizes measuring dynamic interactions between cognitive, affective, and metacognitive processes over time. Challenge 4 calls for incorporating environmental and interpersonal contexts, including collaboration, technology, and embodied cognition. These challenges highlight the need for collaborative approaches to develop standardized measures, synthesize existing findings, and foster methodological innovations. By working together as a research community, we can build more comprehensive theories and effective methods for understanding creativity's cognitive foundations while embracing rather than reducing its inherent complexity.


  • Varieties of divergent thinking: A network analysis of Guilford, Merriefield and Cox (1961)

    by Baptiste Barbot, Lea Marie Naczenski, Matthijs Baas, Claire E. Stevenson


  • Open Access

    Evaluating Creative Short Story Generation in Humans and Large Language Models

    by Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas

    Story-writing is a fundamental aspect of human imagination, relying heavily on creativity to produce narratives that are novel, effective, and surprising. While large language models (LLMs) have demonstrated the ability to generate high-quality stories, their creative story-writing capabilities remain under-explored. In this work, we conduct a systematic analysis of creativity in short story generation across 60 LLMs and 60 people using a five-sentence cue-word-based creative story-writing task. We use measures to automatically evaluate model- and human-generated stories across several dimensions of creativity, including novelty, surprise, diversity, and linguistic complexity. We also collect creativity ratings and Turing Test classifications from non-expert and expert human raters and LLMs. Automated metrics show that LLMs generate stylistically complex stories, but tend to fall short in terms of novelty, surprise and diversity when compared to average human writers. Expert ratings generally coincide with automated metrics. However, LLMs and non-experts rate LLM stories to be more creative than human-generated stories. We discuss why and how these differences in ratings occur, and their implications for both human and artificial creativity.


  • Open Access

    Do large language models solve verbal analogies like children do?

    by Tamar Johnson, Mathilde ter Veen, Rochelle Choenni, Han van der Maas, Ekaterina Shutova, Claire E Stevenson

    Tamar Johnson, Mathilde ter Veen, Rochelle Choenni, Han van der Maas, Ekaterina Shutova, Claire E Stevenson. Proceedings of the 29th Conference on Computational Natural Language Learning. 2025.


  • Open Access

    Automated Assessment of Creativity in Multilingual Narratives

    by Simone A Luchini, Moosa Ibraheem Muhammad, John D. Patterson, Dan Richard Johnson, Matthijs Baas, Baptiste Barbot, Iana Bashmakova, Mathias Benedek, Qunlin Chen, Giovanni Emanuele Corazza, et al.

    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.


  • Open Access

    Playing single-player tasks together: Dyads’ collaborative activities across two games in Math Garden

    by M.S.M. Sachisthal, C. Paans, A.D. Hofman, C.E. Stevenson, H.L.J. van der Maas, I. Molenaar, B.R.J. Jansen


  • Open Access

    Characterising the Creative Process in Humans and Large Language Models

    by Surabhi S. Nath, Peter Dayan, Claire Stevenson

    Large language models appear quite creative, often performing on par with the average human on creative tasks. However, research on LLM creativity has focused solely on \textit{products}, with little attention on the creative \textit{process}. Process analyses of human creativity often require hand-coded categories or exploit response times, which do not apply to LLMs. We provide an automated method to characterise how humans and LLMs explore semantic spaces on the Alternate Uses Task, and contrast with behaviour in a Verbal Fluency Task. We use sentence embeddings to identify response categories and compute semantic similarities, which we use to generate jump profiles. Our results corroborate earlier work in humans reporting both persistent (deep search in few semantic spaces) and flexible (broad search across multiple semantic spaces) pathways to creativity, where both pathways lead to similar creativity scores. LLMs were found to be biased towards either persistent or flexible paths, that varied across tasks. Though LLMs as a population match human profiles, their relationship with creativity is different, where the more flexible models score higher on creativity. Our dataset and scripts are available on \href{https://github.com/surabhisnath/Creative_Process}{GitHub}.


  • Distinct neurocognitive pathways underlying creativity: An integrative approach

    by Matthijs Baas, Claire E. Stevenson, Corinna Perchtold-Stefan, Bernard A. Nijstad, Carsten K. W. De Dreu

    By examining the shared neuro-cognitive correlates of curiosity and creativity, we better understand the brain basis of creativity. However, by only examining shared components, important neuro-cognitive correlates are overlooked. Here, we argue that any comprehensive brain model of creativity should consider multiple cognitive processes and, alongside the interplay between brain networks, also the neurochemistry and neural oscillations that underly creativity.