A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing
This study assesses LLM performance on creative writing, a complex task requiring imagination and style, with implications for AI in creative domains, though it is incremental in benchmarking existing models.
The paper evaluated recent LLMs on English creative writing using a challenging open-ended scenario, finding that some state-of-the-art commercial LLMs matched or slightly outperformed human writers in most dimensions, while open-source LLMs lagged behind.
We evaluate a range of recent LLMs on English creative writing, a challenging and complex task that requires imagination, coherence, and style. We use a difficult, open-ended scenario chosen to avoid training data reuse: an epic narration of a single combat between Ignatius J. Reilly, the protagonist of the Pulitzer Prize-winning novel A Confederacy of Dunces (1980), and a pterodactyl, a prehistoric flying reptile. We ask several LLMs and humans to write such a story and conduct a human evalution involving various criteria such as fluency, coherence, originality, humor, and style. Our results show that some state-of-the-art commercial LLMs match or slightly outperform our writers in most dimensions; whereas open-source LLMs lag behind. Humans retain an edge in creativity, while humor shows a binary divide between LLMs that can handle it comparably to humans and those that fail at it. We discuss the implications and limitations of our study and suggest directions for future research.