Metraipolis › archive › dc_af8cd8e8d2a3
TangPoetryBench: A Multi-Dimensional Benchmark and Rubric-Conditioned Evaluator for Poetry-to-Image Generation — arXiv:2608.11452
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11452
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:15:51.825Z
- SHA-256 of the archived text
f71267424d0c596ae5f74178676076d1e48dc565833e531d2fe8a3851aa1713b- Stable URL of this page
https://metraipolis.com/documento/dc_af8cd8e8d2a3
How to cite
TangPoetryBench: A Multi-Dimensional Benchmark and Rubric-Conditioned Evaluator for Poetry-to-Image Generation — arXiv:2608.11452 — arXiv (en), https://arxiv.org/abs/2608.11452 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af8cd8e8d2a3 (Metraipolis archive dc_af8cd8e8d2a3, sha256 f71267424d0c596ae5f74178676076d1e48dc565833e531d2fe8a3851aa1713b)
BibTeX
@misc{dcaf8cd8e8d2a3,
title = {TangPoetryBench: A Multi-Dimensional Benchmark and Rubric-Conditioned Evaluator for Poetry-to-Image Generation — arXiv:2608.11452},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11452},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af8cd8e8d2a3; sha256 f71267424d0c596ae5f74178676076d1e48dc565833e531d2fe8a3851aa1713b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11452. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-image (T2I) models are increasingly asked to illustrate literary and cultural content, yet we cannot measure how well an image renders the meaning of a poem. The task is many-sided: a good illustration must be visually sound, faithful to the poem's imagery and scene, culturally and stylistically apt, free of spurious text, and true to its emotion, and its deepest requirements, imagery and especially implicit emotion, are never stated in the words. Existing metrics (CLIPScore, BLIPScore, VQAScore) reward literal text-image correspondence and so cannot tell whether an illustration succeeds, let alone why, or even separate the best model from the worst. We introduce TangPoetryBench, a multi-dimensional benchmark of 1,280 images (320 classical Chinese Tang poems x 4 state-of-the-art T2I models) with quality-controlled human annotations across ten dimensions. Analyzing this data, we reveal the shared and model-specific strengths and weaknesses of current T2I models, including their ability to evoke a poem's implicit emotion. We further introduce PoemAutoEvaluator (PAE), an open, rubric-conditioned evaluator that reaches parity with a strong proprietary judge (Claude), generalizes to an unseen generator and a second poetic tradition (Song Ci), and lets the benchmark scale to new images without fresh human annotation. We release the benchmark, annotations, and evaluator. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.11452 — 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 2026-10-19T05:08:46.688Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).