Metraipolis › archive › dc_82142e3d5bee
Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features — arXiv:2608.28986
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28986
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:06:50.531Z
- SHA-256 of the archived text
70f655adf26c07e600000e8bcb2c6a4c82f4ed2a1e7540f7c64a3993f6ef2428- Stable URL of this page
https://metraipolis.com/documento/dc_82142e3d5bee
How to cite
Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features — arXiv:2608.28986 — arXiv (en), https://arxiv.org/abs/2608.28986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_82142e3d5bee (Metraipolis archive dc_82142e3d5bee, sha256 70f655adf26c07e600000e8bcb2c6a4c82f4ed2a1e7540f7c64a3993f6ef2428)
BibTeX
@misc{dc82142e3d5bee,
title = {Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features — arXiv:2608.28986},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28986},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_82142e3d5bee; sha256 70f655adf26c07e600000e8bcb2c6a4c82f4ed2a1e7540f7c64a3993f6ef2428},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 interpretable features. For detection, a logistic regression classifier over these five features attains an average AUC-ROC of 83.60 in zero-shot out-of-distribution detection across seven unseen LLMs, versus 75.84 for the strongest baseline in our comparison, KatFishNet, an absolute gain of 7.76 AUC points and a 10.23% relative improvement; one generator-specific punctuation pattern outside our taxonomy remains a boundary case. For generation, expert evaluation on GPT-5.2 prefers feature-guided poems over the unconstrained baseline, and analyses across GPT-5.2 and Gemini-3 show that targeted length, rhythm, and ending statistics move toward the human distribution. These results suggest that interpretable, language-specific features can bridge the diagnosis and guidance of LLM-generated poetry. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.28986 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:47:52.668Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).