Metraipolis › archive › dc_f08cded2d179
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization — arXiv:2608.23149
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23149
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:45:15.849Z
- SHA-256 of the archived text
10e2d4e198672942afc4d75c6321c540650ede39248c4e2671ff959e40e951a8- Stable URL of this page
https://metraipolis.com/documento/dc_f08cded2d179
How to cite
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization — arXiv:2608.23149 — arXiv (en), https://arxiv.org/abs/2608.23149 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f08cded2d179 (Metraipolis archive dc_f08cded2d179, sha256 10e2d4e198672942afc4d75c6321c540650ede39248c4e2671ff959e40e951a8)
BibTeX
@misc{dcf08cded2d179,
title = {Language Chain in Alignment: Cross-lingual Ranking Preference Optimization — arXiv:2608.23149},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23149},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f08cded2d179; sha256 10e2d4e198672942afc4d75c6321c540650ede39248c4e2671ff959e40e951a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23149. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The alignment of Large Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in other languages. In this paper, we propose Cross-lingual Ranking Preference Optimization~(CRPO), a novel framework that leverages robust preference knowledge from English to facilitate preference alignment in the target language. We design a hierarchical structure within parallel preference pairs across the target language and English to jointly optimize intra- and inter-lingual preferences, thereby enhancing language adaptation and output quality. Building on the LambdaLoss framework, CRPO goes beyond the binary comparison based optimization by providing a relative ranking signal across multiple candidate responses. Our experiments across five languages with varying resource scales demonstrate that CRPO consistently outperforms standard approaches in both instruction-following and knowledge utilization capability. Notably, the robust performance gains observed across various weighting schemes further validate the empirical effectiveness of our hierarchical design in a multilingual setup. Furthermore, our findings highlight that CRPO significantly improves both reward margins and the log-probability of desirable responses, contributing to a more stable preference manifold for cross-lingual alignment. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.23149 — 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 2026-10-18T07:37:52.925Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).