Meta-Learning Preferences for Multilingual LLM Alignment
arXiv cs.CL2w4 min read
arXiv:2607.13315v1 Announce Type: new Abstract: Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical gua