Metraipolis › archive › dc_1cfd2197e68b
Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation — arXiv:2610.19166
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19166
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:23:33.802Z
- SHA-256 of the archived text
f825b81db2eefce27389ff3d339b6d68d88e4bce4c6d28a362787c8213a6d69a- Stable URL of this page
https://metraipolis.com/documento/dc_1cfd2197e68b
How to cite
Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation — arXiv:2610.19166 — arXiv (en), https://arxiv.org/abs/2610.19166 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1cfd2197e68b (Metraipolis archive dc_1cfd2197e68b, sha256 f825b81db2eefce27389ff3d339b6d68d88e4bce4c6d28a362787c8213a6d69a)
BibTeX
@misc{dc1cfd2197e68b,
title = {Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation — arXiv:2610.19166},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19166},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1cfd2197e68b; sha256 f825b81db2eefce27389ff3d339b6d68d88e4bce4c6d28a362787c8213a6d69a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19166. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that correlation is not an appropriate estimate of a metric's evaluation capability and can be unstable across evaluation settings, such as different datasets or languages. Therefore, we propose a regression-based meta-evaluation of metrics that learns on calibrated metric outputs to predict human ratings. We ground this measurement relative to a trivial constant-mean baseline and human agreements to provide a comparable measure of metric capability across evaluation settings. To test our meta-evaluation framework, we developed a large-scale multi-lingual style-personalized text generation (SPTG) benchmark, collecting multiple annotations across 10 topologically diverse languages and four evaluation dimensions, each with varying degrees of subjectivity. We meta-evaluated 32 metrics from three style evaluation paradigms (string-based, embedding-based, and LLM-judges) and their ensembles over these 40 evaluation settings. Our analysis revealed that even simple string- and embedding-based measurements can match strong LLM-judges when calibrated to human ratings. We also identified characteristics of human annotations that determine metric performance, as well as conditions under which a metric ensemble outperforms its individual constituents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.19166 — 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 2026-10-15T19:36:18.168Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).