Wordcraft: Story Writing With Large Language Models

By Ann Yuan, Andy Coenen, Emily Reif, Daphne Ippolito. International Conference on Intelligent User Interfaces, 2022

460 citations recorded by the source corpus.

The latest generation of large neural language models such as GPT-3 have achieved new levels of performance on benchmarks for language understanding and generation. These models have even demonstrated an ability to perform arbitrary tasks without explicit training. In this work, we sought to learn how people might use such models in the process of creative writing. We built Wordcraft, a text editor in which users collaborate with a generative language model to write a story. We evaluated Wordcraft with a user study in which participants wrote short stories with and without the tool. Our results show that large language models enable novel co-writing experiences. For example, the language model is able to engage in open-ended conversation about the story, respond to writers’ custom requests expressed in natural language (such as ”rewrite this text to be more Dickensian”), and generate suggestions that serve to unblock writers in the creative process. Based on these results, we discuss design implications for future human-AI co-writing systems.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/fb5c11bbf63884f75d2da615fbf37a3bcfa2bd20

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models (2023, unknown): “Large Language Models (LLMs) have demonstrated remarkable proficiency in a wide range of natural language processing applications such as content creation, summarization, and dialogue systems (Thoppilan et al., 2022; Yuan et al., 2022; Wei et al., 2022a; Zhang et al., 2023).”
The rise and potential of large language model based agents: a survey (2025, unknown): “Furthermore, they can showcase autonomy through exhibiting creativity like coming up with novel ideas, stories, or solutions that have not been explicitly programmed into them [97,98].”
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text (2023, background): “…(Touvron et al., 2023) and BLOOM (Scao et al., 2022) demonstrate exceptional performance in answering questions (Robinson et al., 2022), writing stories (Fan et al., 2018; Yuan et al., 2022), composing emails, analyzing program code, and thus facilitating daily life and improving work efficiency.”
Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book (2022, methodology): “Across multiple domains, LLMs have been used to support the writing process [13, 44], to generate code [2, 11, 36], to engage students in dialogue [38], and to explain concepts in plain English [23].”
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature (2023, background): “These models have transformed productivity in diverse fields such as news reporting, story writing, and academic research (M Alshater, 2022; Yuan et al., 2022; Christian, 2023).”
Co-Writing Screenplays and Theatre Scripts with Language Models: Evaluation by Industry Professionals (2022, methodology): “Some studies consulted with expert linguists [31], university students in the sciences [42] or humanities [123], and amateur writers [2, 21, 62, 100, 125].”
Cultural bias and cultural alignment of large language models (2023, background): “…Mistral, and LLaMA, which are trained on Internet-scale textual data to process text and produce human-sounding language, are increasingly used by people in all aspects of their life, including education [32], medicine and public health [13, 45], as well as creative and opinion writing [50, 29].”