Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Creating Suspenseful Stories: Iterative Planning with Large Language Models (2402.17119v1)

Published 27 Feb 2024 in cs.CL

Abstract: Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, suspense is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances in LLMs have greatly promoted language generation in general, state-of-the-art LLMs are still unreliable when it comes to suspenseful story generation. We propose a novel iterative-prompting-based planning method that is grounded in two theoretical foundations of story suspense from cognitive psychology and narratology. This theory-grounded method works in a fully zero-shot manner and does not rely on any supervised story corpora. To the best of our knowledge, this paper is the first attempt at suspenseful story generation with LLMs. Extensive human evaluations of the generated suspenseful stories demonstrate the effectiveness of our method.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Automated storytelling via causal, commonsense plot ordering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 5859–5867.
  2. Edward Branigan. 2013. Narrative comprehension and film. Routledge.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Curious case of language generation evaluation metrics: A cautionary tale. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2322–2328, Barcelona, Spain (Online). International Committee on Computational Linguistics.
  5. Interacting with virtual agents in mixed reality interactive storytelling. In Intelligent Virtual Agents: 4th International Workshop, IVA 2003, Kloster Irsee, Germany, September 15-17, 2003. Proceedings 4, pages 231–235. Springer.
  6. Evaluation of text generation: A survey. arXiv preprint arXiv:2006.14799.
  7. Yun-Gyung Cheong and R Michael Young. 2014. Suspenser: A story generation system for suspense. IEEE Transactions on Computational Intelligence and AI in Games, 7(1):39–52.
  8. Neural text generation in stories using entity representations as context. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2250–2260, New Orleans, Louisiana. Association for Computational Linguistics.
  9. Improving the fitness function of an evolutionary suspense generator through sentiment analysis. IEEE Access, 9:39626–39635.
  10. Predicting the effects of suspenseful outcome for automatic storytelling. Knowledge-Based Systems, 209:106450.
  11. Richard Doust and Paul Piwek. 2017. A model of suspense for narrative generation. In Proceedings of the 10th International Conference on Natural Language Generation, pages 178–187, Santiago de Compostela, Spain. Association for Computational Linguistics.
  12. Hierarchical neural story generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 889–898, Melbourne, Australia. Association for Computational Linguistics.
  13. Strategies for structuring story generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2650–2660, Florence, Italy. Association for Computational Linguistics.
  14. Matthew William Fendt and R Michael Young. 2016. Leveraging intention revision in narrative planning to create suspenseful stories. IEEE Transactions on Computational Intelligence and AI in Games, 9(4):381–392.
  15. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5):378.
  16. Richard J Gerrig. 1993. Experiencing narrative worlds: On the psychological activities of reading. Yale University Press.
  17. Richard J Gerrig and Allan BI Bernardo. 1994. Readers as problem-solvers in the experience of suspense. Poetics, 22(6):459–472.
  18. Content planning for neural story generation with aristotelian rescoring. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4319–4338, Online. Association for Computational Linguistics.
  19. A knowledge-enhanced pretraining model for commonsense story generation. Transactions of the Association for Computational Linguistics, 8:93–108.
  20. Story ending generation with incremental encoding and commonsense knowledge. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6473–6480.
  21. Go back in time: Generating flashbacks in stories with event temporal prompts. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1450–1470, Seattle, United States. Association for Computational Linguistics.
  22. Plot writing from pre-trained language models. In Proceedings of the 15th International Conference on Natural Language Generation, pages 52–67, Waterville, Maine, USA and virtual meeting. Association for Computational Linguistics.
  23. Paul E Jose and William F Brewer. 1984. Development of story liking: Character identification, suspense, and outcome resolution. Developmental Psychology, 20(5):911.
  24. Deeptingle. arXiv preprint arXiv:1705.03557.
  25. Michael Lebowitz. 1987. Planning stories. In Proceedings of the 9th annual conference of the cognitive science society, volume 1, page 1.
  26. Zhiyu Lin and Mark O Riedl. 2021. Plug-and-blend: a framework for plug-and-play controllable story generation with sketches. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 17, pages 58–65.
  27. Event representations for automated story generation with deep neural nets. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.
  28. James Richard Meehan. 1976. The Metanovel: Writing Stories by Computer. Yale University.
  29. Brian O’Neill and Mark Riedl. 2014. Dramatis: A computational model of suspense. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 28.
  30. OpenAI. 2022. Chatgpt: A large-scale opendomain chatbot. OpenAI blog.
  31. The Cognitive Structure of Emotions. Cambridge University Press.
  32. Brian O’Neill and Mark Riedl. 2011. Toward a computational framework of suspense and dramatic arc. In Affective Computing and Intelligent Interaction: 4th International Conference, ACII 2011, Memphis, TN, USA, October 9–12, 2011, Proceedings, Part I 4, pages 246–255. Springer.
  33. Towards controllable story generation. In Proceedings of the First Workshop on Storytelling, pages 43–49, New Orleans, Louisiana. Association for Computational Linguistics.
  34. Guiding neural story generation with reader models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7087–7111, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  35. Julie Porteous and Marc Cavazza. 2009. Controlling narrative generation with planning trajectories: the role of constraints. In Interactive Storytelling: Second Joint International Conference on Interactive Digital Storytelling, ICIDS 2009, Guimarães, Portugal, December 9-11, 2009. Proceedings 2, pages 234–245. Springer.
  36. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
  37. 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 Computational Linguistics.
  38. Mark O Riedl and R Michael Young. 2010. Narrative planning: balancing plot and character. Journal of Artificial Intelligence Research, 39(1):217–268.
  39. Melissa Roemmele. 2016. Writing stories with help from recurrent neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30.
  40. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  41. Human evaluation of automatically generated text: Current trends and best practice guidelines. Computer Speech & Language, 67:101151.
  42. Modeling narrative conflict to generate interesting stories. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 6, pages 210–215.
  43. Stephen G Ware and Cory Siler. 2021. Sabre: A narrative planner supporting intention and deep theory of mind. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 17, pages 99–106.
  44. David Wilmot and Frank Keller. 2020. Modelling suspense in short stories as uncertainty reduction over neural representation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1763–1788, Online. Association for Computational Linguistics.
  45. Doc: Improving long story coherence with detailed outline control. arXiv preprint arXiv:2212.10077.
  46. Re3: Generating longer stories with recursive reprompting and revision. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4393–4479, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  47. Plan-and-write: Towards better automatic storytelling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7378–7385.
  48. Towards a computational analysis of suspense: Detecting dangerous situations. arXiv preprint arXiv:2305.06818.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Kaige Xie (11 papers)
  2. Mark Riedl (51 papers)
Citations (6)
View on Semantic Scholar