---
title: "Fiction Flows — paper by Piper et al. (2026) — summary and ideas"
description: "This paper re-examines sequentiality, the language-model metric that Sap et al. (2022) proposed to quantify \"narrative flow.\"… 26 references."
authors: ["Andrew Piper", "Sil Hamilton", "Haiqi Zhou", "Federico Pianzola"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1576/"
doi: "10.18653/v1/2026.acl-long.1576"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/piper-2026-fiction-flows-replication-reinterpretation-narrative/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/piper-2026-fiction-flows-replication-reinterpretation-narrative/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/) / Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality

# Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality

**Authors:** [Andrew Piper](https://md.research.elamur.ai/free/en/authors/andrew-piper/), Sil Hamilton, Haiqi Zhou and Federico Pianzola · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1576/) · [PDF](https://aclanthology.org/2026.acl-long.1576.pdf) · [DOI 10.18653/v1/2026.acl-long.1576](https://doi.org/10.18653/v1/2026.acl-long.1576) · [OpenAlex](https://openalex.org/W7166856248)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
This paper re-examines sequentiality, the language-model metric that Sap et al. (2022) proposed to quantify "narrative flow." Their original finding was that imagined stories score higher than recalled ones. That result came from a single proprietary model (GPT-3) and a formula that conditions on a plot summary. The authors repeat the analysis on the HippoCorpus diary narratives with seven language models of different sizes and architectures. They also vary the formula, adding a context-only variant without the topic term, and they extend the test to passages from published fiction and narrative non-fiction.

Under the original formula, the imagined-over-recalled gap reappears. Once the summary term is removed, however, the gap mostly disappears and becomes model-dependent. This points to an artifact of story–summary mismatch rather than genuine contextual flow. In published texts, fiction consistently beats reality-bound genres under the context-only measure. Mixed-effects models show that this advantage is not explained by conventional coherence indicators. The study matters because it questions what LLM-based predictability actually captures about narrative and calls for better theoretical grounding.

## Key points
- Models tested: GPT-2, GPT-3, LLaMA 3.1, two Qwen 3 variants, SmolLM 3 and Mistral 3.
- The original data is HippoCorpus: 6,854 crowdsourced stories, each falling into one of three conditions: a recalled memory, the same memory recounted again 3–6 months on, or an invented event. All three types share one author-written summary.
- Sequentiality is computed as the per-sentence NLL under the topic alone minus the NLL under topic plus prior context. It is evaluated at history sizes 1–9 and with the full story as history.
- The authors conclude that fiction, not imagination as such, shows a stable sequentiality advantage. This builds on earlier doubts raised by Sunny et al. (2025).
- Code and data are available at github.com/dot-txtlab/fiction-flow. All corpora are English-only, which the authors list as a limitation.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) — University, Ithaca, United States · 120 works · 59,940 citations
- [McGill University](https://md.research.elamur.ai/free/en/universities/mcgill-university/) — University, Montreal, Canada · 87 works · 11,027 citations

📚 Shelves (4): [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 499 works · [📚 Literature and Literary Theory](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/literature-and-literary-theory/) · 519 works

## Cite

Cite as: Andrew Piper, Sil Hamilton, Haiqi Zhou and Federico Pianzola. 2026. Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{piper2026fiction,
  title = {{Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality}},
  author = {Andrew Piper, Sil Hamilton, Haiqi Zhou and Federico Pianzola},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1576},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1576}
}
```

- [← previous Fico: Evaluating Vision-Language Models under Visual Fidelity and Compression at Scale](https://md.research.elamur.ai/free/en/papers/tu-2026-fico-evaluating-vision-language-models/)
- [next → Field of Science and Technology Classification of Academic Documents in Portuguese](https://md.research.elamur.ai/free/en/papers/simoes-2026-field-science-technology-classification-academic/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/)

## References

26 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. R. Balestri and G. Pescatore. 2025. Multi-agent system for ai-assisted extraction of narrative arcs in tv series. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence, volume 1, pages 663–670. [find](https://scholar.google.com/scholar?q=R%2E+Balestri+and+G%2E+Pescatore%2E+2025%2E+Multi%2Dagent+system+for+ai%2Dassisted+extraction+of+narrative+arcs+in+tv+series%2E+In+Proceedings+of+the+17th+International+Conference+on+Agents+and+Artificial+Intellige)
2. Rishi Bommasani, Drew A Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, and 1 others. 2021. [On the opportunities and risks of foundation models](https://md.research.elamur.ai/free/en/papers/bommasani-2021-opportunities-risks-foundation-models/). arXiv e-prints, pages arXiv–2108.
3. C. H. C. Chang, Samuel A. Nastase, and Uri Hasson. 2022. Information flow across the cortical timescale hierarchy during narrative construction. Proceedings of the National Academy of Sciences of the United States of America, 119(51). [find](https://scholar.google.com/scholar?q=C%2E+H%2E+C%2E+Chang%2C+Samuel+A%2E+Nastase%2C+and+Uri+Hasson%2E+2022%2E+Information+flow+across+the+cortical+timescale+hierarchy+during+narrative+construction%2E+Proceedings+of+the+National+Academy+of+Sciences+of+the+)
4. Mihaly Csikszentmihalyi. 1990. Flow: The Psychology of Optimal Experience. Harper and Row, New York. [find](https://scholar.google.com/scholar?q=Mihaly+Csikszentmihalyi%2E+1990%2E+Flow%3A+The+Psychology+of+Optimal+Experience%2E+Harper+and+Row%2C+New+York%2E)
5. Herbert Grabes. 2014. Sequentiality. In Peter Hühn, John Pier, Wolf Schmid, and Jörg Schönert, editors, The Living Handbook of Narratology. Hamburg University, Hamburg. [find](https://scholar.google.com/scholar?q=Herbert+Grabes%2E+2014%2E+Sequentiality%2E+In+Peter+H%C3%BChn%2C+John+Pier%2C+Wolf+Schmid%2C+and+J%C3%B6rg+Sch%C3%B6nert%2C+editors%2C+The+Living+Handbook+of+Narratology%2E+Hamburg+University%2C+Hamburg%2E)
6. Arthur C Graesser, Danielle S McNamara, Max M Louwerse, and Zhiqiang Cai. 2004. Coh-metrix: Analysis of text on cohesion and language. Behavior research methods, instruments, & computers, 36(2):193–202. [find](https://scholar.google.com/scholar?q=Arthur+C+Graesser%2C+Danielle+S+McNamara%2C+Max+M+Louwerse%2C+and+Zhiqiang+Cai%2E+2004%2E+Coh%2Dmetrix%3A+Analysis+of+text+on+cohesion+and+language%2E+Behavior+research+methods%2C+instruments%2C+%26+computers%2C+36%282%29%3A193%E2%80%9320)
7. Arthur C Graesser, Murray Singer, and Tom Trabasso. 1994. Constructing inferences during narrative text comprehension. Psychological review, 101(3):371. [find](https://scholar.google.com/scholar?q=Arthur+C+Graesser%2C+Murray+Singer%2C+and+Tom+Trabasso%2E+1994%2E+Constructing+inferences+during+narrative+text+comprehension%2E+Psychological+review%2C+101%283%29%3A371%2E)
8. Jian Guan, Zhenyu Yang, Rongsheng Zhang, Zhipeng Hu, and Minlie Huang. 2023. Generating coherent narratives by learning dynamic and discrete entity states with a contrastive framework. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Inno… [find](https://scholar.google.com/scholar?q=Jian+Guan%2C+Zhenyu+Yang%2C+Rongsheng+Zhang%2C+Zhipeng+Hu%2C+and+Minlie+Huang%2E+2023%2E+Generating+coherent+narratives+by+learning+dynamic+and+discrete+entity+states+with+a+contrastive+framework%2E+In+Proceedings+)
9. David Herman. 2002. Story Logic: Problems and Possibilities of Narrative. University of Nebraska Press, Lincoln, NE. [find](https://scholar.google.com/scholar?q=David+Herman%2E+2002%2E+Story+Logic%3A+Problems+and+Possibilities+of+Narrative%2E+University+of+Nebraska+Press%2C+Lincoln%2C+NE%2E)
10. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). arXiv preprint arXiv:2001.08361.
11. Walter Kintsch. 1988. The role of knowledge in discourse comprehension: a construction-integration model. Psychological review, 95(2):163. [find](https://scholar.google.com/scholar?q=Walter+Kintsch%2E+1988%2E+The+role+of+knowledge+in+discourse+comprehension%3A+a+construction%2Dintegration+model%2E+Psychological+review%2C+95%282%29%3A163%2E)
12. Shayne Longpre, Gregory Yauney, Emily Reif, Katherine Lee, Adam Roberts, Barret Zoph, Denny Zhou, Jason Wei, Kevin Robinson, David Mimno, and 1 others. 2024. A pretrainer’s guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity. In Proceedings of the 2024 Con… [find](https://scholar.google.com/scholar?q=Shayne+Longpre%2C+Gregory+Yauney%2C+Emily+Reif%2C+Katherine+Lee%2C+Adam+Roberts%2C+Barret+Zoph%2C+Denny+Zhou%2C+Jason+Wei%2C+Kevin+Robinson%2C+David+Mimno%2C+and+1+others%2E+2024%2E+A+pretrainer%E2%80%99s+guide+to+training+data%3A+Mea)
13. Ben Naismith, Phoebe Mulcaire, and Jill Burstein. 2023. [Automated evaluation of written discourse coherence using gpt-4](https://md.research.elamur.ai/free/en/papers/naismith-2023-automated-evaluation-written-discourse-coherence/). In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 394–403.
14. Federico Pianzola. 2024. Dynamical systems, literary theory, and the computational modelling of narrative. Interdisciplinary Science Reviews, 49(2):222–236. [find](https://scholar.google.com/scholar?q=Federico+Pianzola%2E+2024%2E+Dynamical+systems%2C+literary+theory%2C+and+the+computational+modelling+of+narrative%2E+Interdisciplinary+Science+Reviews%2C+49%282%29%3A222%E2%80%93236%2E)
15. Federico Pianzola, Giuseppe Riva, Karin Kukkonen, and Fabrizio Mantovani. 2021. Presence, flow, and narrative absorption: an interdisciplinary theoretical exploration with a new spatiotemporal integrated model based on predictive processing. Open Research Europe, 1. [find](https://scholar.google.com/scholar?q=Federico+Pianzola%2C+Giuseppe+Riva%2C+Karin+Kukkonen%2C+and+Fabrizio+Mantovani%2E+2021%2E+Presence%2C+flow%2C+and+narrative+absorption%3A+an+interdisciplinary+theoretical+exploration+with+a+new+spatiotemporal+integra)
16. Roger Schank and Robert P. Abelson. 1977. Scripts, Plans, Goals and Understanding. Lawrence Erlbaum, Hillsdale, NJ. [find](https://scholar.google.com/scholar?q=Roger+Schank+and+Robert+P%2E+Abelson%2E+1977%2E+Scripts%2C+Plans%2C+Goals+and+Understanding%2E+Lawrence+Erlbaum%2C+Hillsdale%2C+NJ%2E)
17. Hyunmi Song, Byung Yoon Park, Hyun Park, and Woo Min Shim. 2021. Cognitive and neural state dynamics of narrative comprehension. The Journal of Neuroscience, 41(43):8972–8990. [find](https://scholar.google.com/scholar?q=Hyunmi+Song%2C+Byung+Yoon+Park%2C+Hyun+Park%2C+and+Woo+Min+Shim%2E+2021%2E+Cognitive+and+neural+state+dynamics+of+narrative+comprehension%2E+The+Journal+of+Neuroscience%2C+41%2843%29%3A8972%E2%80%938990%2E)
18. Amal Sunny, Advay Gupta, Yashashree Chandak, and Vishnu Sreekumar. 2025. From stories to statistics: Methodological biases in llm-based narrative flow quantification. In The SIGNLL Conference on Computational Natural Language Learning. [find](https://scholar.google.com/scholar?q=Amal+Sunny%2C+Advay+Gupta%2C+Yashashree+Chandak%2C+and+Vishnu+Sreekumar%2E+2025%2E+From+stories+to+statistics%3A+Methodological+biases+in+llm%2Dbased+narrative+flow+quantification%2E+In+The+SIGNLL+Conference+on+Compu)
19. B. A. K. Thissen, Winfried Menninghaus, and Wolff Schlotz. 2018. Measuring optimal reading experiences: The reading flow short scale. Frontiers in Psychology, 9. [find](https://scholar.google.com/scholar?q=B%2E+A%2E+K%2E+Thissen%2C+Winfried+Menninghaus%2C+and+Wolff+Schlotz%2E+2018%2E+Measuring+optimal+reading+experiences%3A+The+reading+flow+short+scale%2E+Frontiers+in+Psychology%2C+9%2E)
20. Sean Wilner, Daniel Woolridge, and Madeleine Glick. 2021. Narrative embedding: Re-Contextualization through attention. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1393–1405, Online and Punta Cana, Dominican Republic. Association for Computational… [find](https://scholar.google.com/scholar?q=Sean+Wilner%2C+Daniel+Woolridge%2C+and+Madeleine+Glick%2E+2021%2E+Narrative+embedding%3A+Re%2DContextualization+through+attention%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Pr)
21. Jinming Zhang and Yunfei Long. 2025. MLD-EA: Check and complete narrative coherence by introducing emotions and actions. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1892–1907, Abu Dhabi, UAE. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jinming+Zhang+and+Yunfei+Long%2E+2025%2E+MLD%2DEA%3A+Check+and+complete+narrative+coherence+by+introducing+emotions+and+actions%2E+In+Proceedings+of+the+31st+International+Conference+on+Computational+Linguistic)
22. John Pier. 2016. The configuration of narrative sequences. In Raphaël Baroni and Françoise Revaz, editors, Narrative Sequence in Contemporary Narra-tologies, pages 20–36. Ohio State University Press. [find](https://scholar.google.com/scholar?q=John+Pier%2E+2016%2E+The+configuration+of+narrative+sequences%2E+In+Rapha%C3%ABl+Baroni+and+Fran%C3%A7oise+Revaz%2C+editors%2C+Narrative+Sequence+in+Contemporary+Narra%2Dtologies%2C+pages+20%E2%80%9336%2E+Ohio+State+University+Press%2E)
23. Andrew Piper. 2022. The conlit dataset of contemporary literature. Journal of Open Humanities Data, 8. [find](https://scholar.google.com/scholar?q=Andrew+Piper%2E+2022%2E+The+conlit+dataset+of+contemporary+literature%2E+Journal+of+Open+Humanities+Data%2C+8%2E)
24. Hannah Rashkin, Asli Celikyilmaz, Yejin Choi, and Jianfeng Gao. 2020. PlotMachines: Outline-conditioned generation with dynamic plot state tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4274–4295, Online. Association for Computation… [find](https://scholar.google.com/scholar?q=Hannah+Rashkin%2C+Asli+Celikyilmaz%2C+Yejin+Choi%2C+and+Jianfeng+Gao%2E+2020%2E+PlotMachines%3A+Outline%2Dconditioned+generation+with+dynamic+plot+state+tracking%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+)
25. Maarten Sap, Eric Horvitz, Yejin Choi, Noah A Smith, and James Pennebaker. 2020. Recollection versus imagination: Exploring human memory and cognition via neural language models. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 1970–1978. [find](https://scholar.google.com/scholar?q=Maarten+Sap%2C+Eric+Horvitz%2C+Yejin+Choi%2C+Noah+A+Smith%2C+and+James+Pennebaker%2E+2020%2E+Recollection+versus+imagination%3A+Exploring+human+memory+and+cognition+via+neural+language+models%2E+In+Proceedings+of+the)
26. Maarten Sap, Anna Jafarpour, Yejin Choi, Noah A Smith, James W Pennebaker, and Eric Horvitz. 2022. Quantifying the narrative flow of imagined versus autobiographical stories. Proceedings of the National Academy of Sciences, 119(45):e2211715119. [find](https://scholar.google.com/scholar?q=Maarten+Sap%2C+Anna+Jafarpour%2C+Yejin+Choi%2C+Noah+A+Smith%2C+James+W+Pennebaker%2C+and+Eric+Horvitz%2E+2022%2E+Quantifying+the+narrative+flow+of+imagined+versus+autobiographical+stories%2E+Proceedings+of+the+Nation)

*Updated 1 November 2026*