CoChat

The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.

Nabokov's Cards: An AI Assisted Prewriting System to Support Bottom-Up Creative Writing

Carrera, Dashiel, Zhao, Zixin, Ajin Thomas, Ashish, Wigdor, Daniel · 2025 · Proceedings of the 2025 Conference on Creativity and Cognition

Abstract

We introduce Nabokov’s Cards, a creativity support tool that uses Large Language Models (LLMs) to support prewriting. Inspired by the writing process of Vladimir Nabokov, Nabokov’s Cards enables prewriting ideation by providing users with an interface to write idea fragments on notecards and combine them into new sentences or concepts using an LLM. We evaluated Nabokov’s Cards through a one-week user study with professional creative writers (n=13) to explore writers’ prewriting processes and learn about their usage of the system. Through our interviews, we found that writers characterized prewriting as a long, amorphous process that involved observations of the real world and the accumulation of idea fragments. Writers in our study found that Nabokov’s Cards facilitated prewriting through nonlinear interactions, divergent thinking, play, improvisation, and reflection. It also encouraged innovative approaches among writers that surpassed the clichés and redundancy often found within AI generated text today. We note how future AI co-writing systems may benefit from designs that facilitate prompt engineering and modular thinking.

Overview

Integrity signals

Registry

Crossref · 10.1145/3698061.3726916

Cites

58 of 58 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 18

  1. Seungho Baek Hyerin Im Jiseung Ryu Juhyeong Park and Takyeon Lee. 2023. PromptCrafter: crafting text-to-image prompt through mixed-initiative dialogue with LLM. arXiv preprint arXiv:https://arXiv.org/abs/2307.08985 (2023). · arXiv
  2. Ismail Baroudy. 2008. A procedural approach to process theory of writing: Prewriting techniques. The International Journal of Language Society and Culture 24 4 (2008) 45–52.
  3. Donald Barthelme. 1985. Not-knowing. The Georgia Review 39 3 (1985) 509–522.
  4. Alex Calderwood, Vivian Qiu, Katy Ilonka Gero, and Lydia B. Chilton. [n. d.]. How Novelists Use Generative Language Models: An Exploratory User Study. In Conf. on Intelligent User Interfaces Workshop (2020-03-05). ACM.
  5. Tuhin Chakrabarty Vishakh Padmakumar Faeze Brahman and Smaranda Muresan. 2023. Creativity support in the age of large language models: An empirical study involving emerging writers. arXiv preprint arXiv:https://arXiv.org/abs/2309.12570 (2023). · arXiv
  6. Hai Dang Lukas Mecke Florian Lehmann Sven Goller and Daniel Buschek. 2022. How to prompt? Opportunities and challenges of zero-and few-shot learning for human-AI interaction in creative applications of generative models. arXiv preprint arXiv:https://arXiv.org/abs/2209.01390 (2022). · arXiv
  7. Michael Koch, Kai von Luck, Jan Schwarzer, and Susanne Draheim. 2018. The novelty effect in large display deployments–Experiences and lessons-learned for evaluating prototypes. In Proceedings of 16th European conference on computer-supported cooperative work-exploratory papers. European Society for Socially Embedded Technologies (EUSSET).
  8. Jonathan Mamou, Hang Le, Miguel A Del Rio, Cory Stephenson, Hanlin Tang, Yoon Kim, and SueYeon Chung. 2020. Emergence of separable manifolds in deep language representations. In Proceedings of the 37th International Conference on Machine Learning(ICML’20). JMLR.org, Article 623, 11 pages.
  9. Vladimir Nabokov. [n. d.]. The Original of Laura. Knopf Doubleday Publishing Group. Google-Books-ID: Dw4VsZ1944UC.
  10. Anna North. [n. d.]. What Kind of Writer Are You: Cook or Baker?https://lithub.com/what-kind-of-writer-are-you-cook-or-baker/
  11. Alexandria Peary. 2016. The terrain of prewriting. Journal of Creative Writing Studies 2 1 (2016) 1.
  12. Georges Perec. [n. d.]. A Void. The Harvill Press.
  13. Kevin Pu KJ Feng Tovi Grossman Tom Hope Bhavana Dalvi Mishra Matt Latzke Jonathan Bragg Joseph Chee Chang and Pao Siangliulue. 2024. IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback. arXiv preprint arXiv:https://arXiv.org/abs/2410.04025 (2024). · arXiv
  14. George Rylands. 1928. Words and poetry. Hogarth Press.
  15. 10.1145/2702123.2702383 · DOI
  16. Alexander Theroux. 2009. In the Cards A Last Hand. Wall Street Journal 20 (2009).
  17. Mónica de la Torre. [n. d.]. Channeling Curiosity Into Language: How a Diverse Array of Influences Feeds Poetic Development. https://lithub.com/channeling-curiosity-into-language-how-a-diverse-array-of-influences-feeds-poetic-development/
  18. Daijin Yang, Yanpeng Zhou, Zhiyuan Zhang, Toby Jia-Jun Li, and Ray LC. 2022. AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing. In Joint Proceedings of the ACM IUI Workshops , Vol. 10. CEUR-WS Team, 1–11.

Cited by

See all 7

Metadata

Authors
Carrera, D., Zhao, Z., Ajin Thomas, A., & Wigdor, D.
Affiliations
  • University of Toronto (CA)
  • University of Toronto, Toronto, Ontario, Canada
Venue
Proceedings of the 2025 Conference on Creativity and Cognition
Publisher
ACM
Published
2025-06-22
Pages
546-559
OpenAlex
W4411534484
Cited by
6
References
54
Citations by year
2026: 6
FWCI
47.76
Type
conference paper
Language
en
Open access
closed
Locations
Creativity and Cognition (publishedVersion)
Topics
  • Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Artistic and Creative Research
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
  • Social Sciences › Education › Artificial Intelligence in Education
Keywords
Vladimir Nabokov, cards, creative writing, prewriting, AI-assisted writing, writing support systems, generative AI in writing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.