POEMetric reveals that top LLMs match humans on poem form and theme but score substantially lower on creativity, idiosyncrasy, emotional resonance, imagery, literary devices, and overall quality.
1 - Strongly disagree 2 - Disagree 3 - Neutral 4 - Agree 5 - Strongly agree
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
POEMetric: The Last Stanza of Humanity
POEMetric reveals that top LLMs match humans on poem form and theme but score substantially lower on creativity, idiosyncrasy, emotional resonance, imagery, literary devices, and overall quality.