Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku
This study demonstrates that while human participants can sometimes distinguish AI-generated haiku from human-written ones, their judgments are heavily influenced by aesthetic qualities like fluency and poeticness rather than actual authorship, suggesting that as large language models improve, surface-level creative plausibility increasingly undermines reliable human detection of AI-generated poetry.
Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.