EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Narrative Consistency in Large Language Model-Generated Stories: A Survey

Keunhyeung Park, Seunguk Yu, Jinhee Jang, Hoejoon Kwon, Byeonggeuk Lim, Youngbin Kim

IEEE Access · 2026 · 14 · 105794-105819

DOI: 10.1109/access.2026.3710595 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Keunhyeung Park und 5 weiteren Autor:innen. Die Arbeit nennt 124 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chung-Ang University Graduate Research Scholarship.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models have advanced long-form story generation, yet the resulting narratives often fail to preserve facts, states, and relationships established earlier in the same text. This survey examines the problem as narrative consistency, defined as the task-conditioned preservation of binding propositions in the operative narrative state. Using a targeted evidence-mapping strategy, we analyze 90 papers, with a literature search cutoff of April 23, 2026, covering long-form story generation, narrative evaluation, consistency detection, and mitigation strategies. We distinguish narrative consistency from factuality, faithfulness, surface coherence, and hallucination by centering the dynamically accumulated evidence of the story itself. The survey organizes consistency judgments around three evidence sources, namely story-internal propositions, source-or-canon evidence, and external-world knowledge, as determined by task conditions that specify which source is binding. We introduce a four-category, fourteen-subtype taxonomy comprising World and Setting, Character-Agentive, Event-Structural, and Narration and Discourse categories. We use the taxonomy as a common reference frame for analyzing benchmark coverage, detection methods, mitigation strategies, and open challenges, highlighting where current work concentrates and where coverage remains thin. We also separate legitimate creative extension from task-inconsistent additions that contradict, revise, or exceed the permitted generation setting. The survey closes by identifying needs for evidence-grounded oracles, subtype-aware calibration, omission and discourse-level failure evaluation, and task-conditioned verification.

Förderung

  • Chung-Ang University Graduate Research Scholarship

Zitieren

APA

Park, K., Yu, S., Jang, J., Kwon, H., Lim, B., & Kim, Y. (2026). Narrative Consistency in Large Language Model-Generated Stories: A Survey. IEEE Access, 14, 105794-105819. https://doi.org/10.1109/access.2026.3710595

Vancouver

Park K, Yu S, Jang J, Kwon H, Lim B, Kim Y. Narrative Consistency in Large Language Model-Generated Stories: A Survey. IEEE Access. 2026;14:105794-105819. doi:10.1109/access.2026.3710595

BibTeX
@article{Park2026,
  author = {Park, Keunhyeung and Yu, Seunguk and Jang, Jinhee and Kwon, Hoejoon and Lim, Byeonggeuk and Kim, Youngbin},
  title = {Narrative Consistency in Large Language Model-Generated Stories: A Survey},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {105794--105819},
  doi = {10.1109/access.2026.3710595}
}
Kostenlos starten →