AI summaryⓘ
The authors explore how generative AI can be used to simulate the creation of literature in a controlled and large-scale way, which could help study cultural production. They note that current AI systems still struggle to reliably create high-quality, book-length stories that match specific cultural or stylistic rules. However, they review research on important parts needed for this, like modeling human behavior with AI, creating consistent stories, and adjusting AI knowledge predictably. The authors also share experiments comparing AI-generated texts to human-written novels, showing some initial success on producing texts within a certain style. They discuss future plans to create more complete AI simulations of literary history.
generative AIliterary simulationcultural productionnarrative generationstylometrymultiagent systemscounterfactual simulationtext coherenceAI proxiesliterary-historical modeling
Abstract
Generative artificial intelligence (AI) systems open new possibilities for experimentation in literary studies via controlled, grounded, large-scale, low-cost simulations of cultural production. Current systems have not yet been shown to produce high-quality, book-length narrative texts that reliably reflect arbitrarily specified cultural constraints or stylistic features. But there exists substantial relevant research on each of the components required for literary-historical simulation. These include the use and validation of AI systems as proxies for differentiable human populations; the narrative and stylistic properties of AI-generated texts; the stability and coherence of multiagent, multiturn AI simulations of human actors; and technical methods through which to alter in predictable ways the knowledge and behavior of generative systems. Together, these areas could provide a starting point for more ambitious AI-based modeling of cultural systems of literary production. We describe the possibilities and challenges of simulation-based experiments in literary studies, summarize the current state of the art in relevant fields, and explain key technical aspects of the work. To provide an example directly relevant to literary scholars, we present the results of experiments on literary text generation, including comparisons to high-status, human-authored novels. Our results include the first demonstration of (limited) in-distribution outputs by AI models in this domain. We conclude with a description of future work on full counterfactual literary-historical simulations using AI.