SOURCE-LINKED INTELLIGENCE

Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

LLMs often struggle with modern Korean poetry, producing outputs that resemble "line-broken prose." We address two coupled tasks: detecting whether a Korean poem is human- or LLM-authored, and guiding LLMs to generate poetry closer in form to human writing. We quantify the human-LLM gap along four form-level linguistic dimensions: output length (Volume), the diversity and connective use of line-final forms (Structure Variation), the irregularity of line lengths (Rhythmic Irregularity), and adherence to standard orthography (Normative Adherence). We operationalize these dimensions as five inter

Read original source ↗ Open in workspace

recordType

paper

region

Global