Article In: Narrative Inquiry: Online-First Articles
No humans-in-the-loop
The people-less stories generated by GPT
This content is being prepared for publication; it may be subject to changes.
Abstract
In the last two years, numerous news outlets and academic articles have claimed that GPT-produced text is
indistinguishable from human-written text across several genres. In this essay, we argue that not only does GPT not write fictional
narratives like a human, it also often fails to write about humans. We demonstrate how the distribution of
stylistic features that we can use as proxies for key elements of narrative, including the frequency of named entities, dialogue, pronouns
and the second person, can reliably distinguish between human and GPT-generated text. We argue that these textual markers point to a deeper
conceptual difference between human-written and GPT-generated text — GPT texts contain few characters, rarely feature a characterized
narrator, and describe inanimate objects more often than people or characters. In sum, the thousands of GPT-generated narratives we analyzed
struggled to meet the commonly accepted definition of narrative in contemporary narrative theory, which emphasizes the centrality of the
human experience in narrative representation, and encompasses the broader rhetorical communication circuit in which narrative takes
place.
Article outline
- Introduction
- Literature review
- Data
- Character
- Method
- Results
- Qualitative analysis
- Communication circuit
- Method
- Results
- Qualitative Analysis
- Conclusion
- Notes
- Author queries
Works Cited
References (46)
Bamman, D., Underwood, T., & Smith, N. (2014). A
Bayesian mixed effects model of literary character. Proceedings of the Association for Computational
Linguistics, (Volume 1: Long
Papers), 370–379. Association for Computational Linguistics.
Bissell, A., Paulin, E., & Piper, A. (2025). A
theoretical framework for evaluating narrative surprise in large language models. Proceedings of the 7th
Workshop on Narrative Understanding, 26–35. Association for Computational Linguistics.
Bro, N. (2025). A
frustratingly easy way of extracting political networks from text. PLOS
ONE, 20(1), e0313149.
Brunyé, T., Ditman, T., Mahoney, C. R., & Taylor, H. A. (2011). Better
you than I: Perspectives and emotion simulation during narrative comprehension. Journal of Cognitive
Psychology, 23(5), 659–666.
Chakarian, E. (2025, March 13). Dave
Eggers on OpenAI’s new creative writing bot: “A cheap party trick.” The San Francisco
Standard. [URL]
Cheng, M., Durmus, E., & Jurafsky, D. (2023). Marked
personas: Using natural language prompts to measure stereotypes in language models. Proceedings of the 61st
Annual Meeting of the Association for Computational Linguistics (Volume 1: Long
Papers), 1504–1532. Association for Computational Linguistics.
Fields, S., Lyans Cole, C., Oei, C., & Chen, A. T. (2023). Using
named entity recognition and network analysis to distinguish personal networks from the social milieu in nineteenth-century Ottoman–Iraqi
personal diaries. Digital Scholarship in the
Humanities, 38(1), 66–86.
Fludernik, M. (2001). Commentary:
Narrative voices: Ephemera or bodied beings. New Literary
History, 32(3), 707–710. [URL]
Gezari, J. (2022). Jane
Eyre’s style. In D. Tyler (Ed.), On
style in Victorian fiction (130–149). Cambridge University Press.
Guldi, J. (2023). On
memory. In The dangerous art of text mining: A methodology for digital
history. Cambridge University Press.
Haverals, W., & Martin, M. (2025). Everyone
prefers human writers, including AI. arXiv. [URL]
Kirilloff, G. (2022). Computation
as context: New approaches to the close/distant reading debate. College
Literature, 49(1), 1–25.
Kirilloff, G., Carroll, C., Daboul, Z., Frank, A., Khan, R., Hinrichs-Morrow, M., & Weingart, R. (2025). “Written
in the style of”: ChatGPT and the literary canon. Harvard Data Science
Review, 7(4).
Li, L., & Bamman, D. (2021). Gender
and representation bias in GPT-3 generated stories. Proceedings of the Third Workshop on Narrative
Understanding, 48–55. Association for Computational Linguistics.
Mar, R. A., Oatley, K., & Peterson, J. B. (2009). Exploring
the link between reading fiction and empathy: Ruling out individual differences and examining
outcomes. Communications, 34(4), 407–428.
Marshall, R. (2020). Reading
fiction: The benefits are numerous. British Journal of General
Practice, 70(691), 79.
Menon, T. (2019). Keeping
count: Direct speech in the nineteenth-century British
novel. Narrative, 27(2), 160–181.
McGurl, M. (2009). The
Program Era: Postwar Fiction and the Rise of Creative Writing. Harvard University Press.
Muzny, G., Algee-Hewitt, M., & Jurafsky, D. (2017). Dialogism
in the novel: A computational model of the dialogic nature of narration and quotations. Digital Scholarship
in the
Humanities, 32(2), December 2017, 31–52.
Pennington, H. L. (2018). Creating
identity in the Victorian fictional autobiography. University of Missouri Press.
Phelan, J. (2017). Somebody
telling somebody else: A rhetorical poetics of narrative. Ohio State University Press.
Piper, A., So, R. J., and Bamman, D. (2021). Narrative
Theory for Computational Narrative Understanding. Proceedings of the 2021 Conference on Empirical Methods
in Natural Language Processing, 298–311. Association for Computational Linguistics.
Piper, A. (2023). What
do characters do? The embodied agency of fictional characters. Journal of Computational Literary
Studies, 2(1), 1–12.
Porter, B., & Machery, E. (2024). AI-generated
poetry is indistinguishable from human-written poetry and is rated more favorably. Scientific
Reports 14 (26133).
Sorlin, S. (2022). The
stylistics of “you’: Second-person pronoun and its pragmatic effects. Cambridge University Press.
Stewart, G. (1996). Dear
reader: The conscripted audience in nineteenth-century British fiction. Johns Hopkins University Press.
Tomlinson, K., Jaffe, S., Wang, W., Counts, S., & Suri, S. (2025). Working
with AI: Measuring the applicability of generative AI to occupations. arXiv. [URL]
Underwood, T., Bamman, D., & Lee, S. (2018). The
transformation of gender in English-language fiction. Journal of Cultural
Analytics, 3(2).
Walsh, M., Preus, A., & Gronski, E. (2024). Does
ChatGPT have a poetic style? Proceedings of the Computational Humanities Research
Conference 2024, (Vol. 3834), 1201–1219. [URL]
Walsh, M., Preus, A., & Antoniak, M. (2024). Sonnet
or not, bot? Poetry evaluation for large models and datasets. Findings of the Association for Computational
Linguistics: EMNLP 2024, 15568–15603. [URL].
Wang, Y., & Kreminski, M. (2025). Can
LLMs generate good stories? Insights and challenges from a narrative planning perspective. IEEE Conference
on Games, 1–8.
Warhol, R. R. (1989). Gendered
interventions: Narrative discourse in the Victorian novel. Rutgers University Press.