Files and links (2)
Preprint VersionCC BY V4.0, Open Access
Preprint
A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing
arXiv , Vol.12 October 2023
Cornell University
2023
Abstract
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.
Details
- Title
- A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing
- Authors
- Carlos Gómez-Rodríguez (Author) - Universidade da CoruñaPaul Williams (Author) - University of the Sunshine Coast, Queensland, School of Business and Creative Industries
- Publication details
- arXiv , Vol.12 October 2023
- Publisher
- Cornell University
- Date published
- 2023
- DOI
- 10.48550/arxiv.2310.08433
- ISSN
- 2331-8422
- Grant note
- European Research Council (ERC)
- Organisation Unit
- School of Business and Creative Industries; Indigenous and Transcultural Research Centre; University of the Sunshine Coast, Queensland; Sustainability Research Cluster
- Language
- English
- Record Identifier
- 99971190202621
- Output Type
- Preprint
Metrics
2 File views/ downloads
118 Record Views