Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study investigates the distinguishing attributes of English poetry generated by AI versus that written by humans, addressing the challenge of classification in the context of increasing AI-generated content. By employing a zero-shot detection pipeline, the researchers analyze a dataset of both human and AI poems to identify key characteristics that contribute to misclassification. The findings reveal critical attributes that not only enhance the accuracy of classification but also inform improvements in AI detection systems, highlighting the nuanced nature of poetry and its implications for academic integrity.
AI-generated poetry is often indistinguishable from human-written works, but this study uncovers specific attributes that can improve detection accuracy.
With the advancement of AI technologies, Generative AI (GenAI) and human written text have become nearly indistinguishable. Additionally, the global standardization of AI chatbots made academic malpractice more frequent. Furthermore, existing research indicates GenAI poems are the most difficult to distinguish even without any modification thus, GenAI poems are naturally deemed human-like by modern detectors. However, the objectivity of such dissertations needs to be verified against modern detection tools but the subjectivity of poetry and the black-box nature of the modern LLMs (Large Language Models) architectures made verification of such work quite complicated. Hence, the main objective of the research is to deduce the attributes of English poetry that contribute classification and misclassification of both human and AI poems and provide corroborating or contradicting evidence to the poetry distinguishability claim. For such characterizations, we propose a Zero-shot detection pipeline with a dataset consisting of both human and AI poems to verify the distinguishability of human and AI creation and extract the aforementioned crucial attributes for accurate classification. Extraction of such attributes provides benefits in two ways: firstly, it reduces the margin of training needed as only the poems based on misclassifying attributes need to be trained and fine tuned and finally provides a critical insight to the GenAI detection dilemma to strengthen the modern detection pipelines.