Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing

TL;DR

This study investigates how observing AI-generated text influences human creative writing, demonstrating that exposure to machine-produced examples enhances the perceived storytelling quality of human-authored sentences.

Contribution

It introduces an 'inspiration through observation' approach showing that human writers produce more storiable sentences after viewing AI-generated examples, advancing collaborative AI-human creative processes.

Findings

Human authors' sentences were judged more storiable after observing generated examples.

Storiability increased with greater semantic content derived from AI examples.

The approach supports AI-human collaboration without direct copying.

Abstract

Getting machines to generate text perceived as creative is a long-pursued goal. A growing body of research directs this goal towards augmenting the creative writing abilities of human authors. In this paper, we pursue this objective by analyzing how observing examples of automatically generated text influences writing. In particular, we examine a task referred to as sentence infilling, which involves transforming a list of words into a complete sentence. We emphasize "storiability" as a desirable feature of the resulting sentences, where "storiable" sentences are those that suggest a story a reader would be curious to hear about. Both humans and an automated system (based on a neural language model) performed this sentence infilling task. In one setting, people wrote sentences on their own; in a different setting, people observed the sentences produced by the model while writing their own sentences. Readers then assigned storiability preferences to the resulting sentences in a subsequent evaluation. We find that human-authored sentences were judged as more storiable when authors observed the generated examples, and that storiability increased as authors derived more semantic content from the examples. This result gives evidence of an "inspiration through observation" paradigm for human-computer collaborative writing, through which human writing can be enhanced by text generation models without directly copying their output.