Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
- 类型：arxiv
- 标识：2608.23149
- 链接：https://arxiv.org/abs/2608.23149
- 主分类：risk
- 形态：method
- TLDR：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 qualit
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-08-31-agent-rag-longcontext-candidates.json