The findings suggest that HWAMW facilitates restorying and offers a valuable paradigm for AI-assisted writing, wherein LLMs do not tell their stories but rather help us see greater potential in the stories the authors tell.
Abstract
AI-assisted writing can flatten meaning in human storytelling, enabling the production of homogeneous outputs without the intentional effort and sense-making writing entails. To address this challenge, we present The House with a Million Windows (HWAMW), an LLM-based interactive fiction system designed to help users explore both the breadth and depth of potential meanings within their personal stories -- drawing on a psychological paradigm called the restorying intervention. In HWAMW, users play through a text-based narrative in which they tell a story, then encounter a set of LLM-generated"windows"reframing it according to different literary styles. Empirical evidence shows that HWAMW increases users'sense of narrative identity, while an expert review explores how this effect is achieved. Our findings suggest that HWAMW facilitates restorying and offers a valuable paradigm for AI-assisted writing, wherein LLMs do not tell our stories but rather help us see greater potential in the stories we tell.
Drawing from narratological frameworks like those produced by Marie-Laure Ryan and Mieke Bal, this essay provides strategies for those seeking to immerse readers using perspectivised characters in Science Fiction. An emphasis is placed on how these strategies are applied in speculative storyworlds that feature ontologi...
This paper examines how literature, games, and film influence one another and reshape narrative form in the digital media environment. Classical narratology presupposes a linear text read from beginning to end in a single order, and therefore has inherent limitations in accounting for digital narratives that branch int...
Ho-seung Sim· The Global Association of Ap...· 0 citations
This paper compares 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg to find that human-authored texts predominantly employ "action space,"grounding narratives in embodied character-environment interaction, whereas LLMs systematically overproduce "perceived s...
Katrin Rohrbacher, Björn Nieth, Emmanuelle Salin et al.· 0 citations
Creative writing pedagogy has often privileged imagination as the defining characteristic of storytelling. Yet many young writers struggle not because they lack imagination, but because they believe they have nothing worth writing about. This paper proposes a pedagogical model that repositions observation, critical thi...
Suhaile Azavedo· International Journal of Eng...· 0 citations
We-narratives are a less common variant of the it-narrative, in which a story is written from the perspective of an object or non-human entity. As a first-person plural perspective, a we-narrative assumes affiliation and understanding among the community voice and differs from a multi-voice narrative. The author’s own...
Paula Read· European journal of life wri...· 0 citations
The article situates LLM-generated narratives within the
twenty-first-century story economy by asking how they rework the storytelling patterns
shaped by social media, algorithmic optimization, and the pursuit of the “compelling
story.” Previous research has shown that stories gaining traction on social media conf...
Juha Raipola, Maria Mäkelä, Samuli Björninen et al.· Narrative Inquiry· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduSep 2, 2026
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, human-editable specifications. The post Flint: A visualization language for the AI era appeared first on Microsoft Research.
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.