Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
This addresses the scalability issue in multilingual safety alignment for LLMs, offering a practical solution for deployment across linguistic communities, though it is incremental as it builds on existing monolingual pipelines.
The paper tackles the problem of resource-intensive multilingual safety alignment for large language models by proposing a plug-and-play Multi-Lingual Consistency loss that improves alignment across multiple languages using only multilingual prompts, without needing additional response-level supervision in low-resource languages, and demonstrates effectiveness with improved cross-lingual generalization.
The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources, either through large-scale, high-quality supervision in the target language or through pairwise alignment with high-resource languages, which limits scalability. In this work, we propose a resource-efficient method for improving multilingual safety alignment. We introduce a plug-and-play Multi-Lingual Consistency (MLC) loss that can be integrated into existing monolingual alignment pipelines. By improving collinearity between multilingual representation vectors, our method encourages directional consistency at the multilingual semantic level in a single update. This allows simultaneous alignment across multiple languages using only multilingual prompt variants without requiring additional response-level supervision in low-resource languages. We validate the proposed method across different model architectures and alignment paradigms, and demonstrate its effectiveness in enhancing multilingual safety with limited impact on general model utility. Further evaluation across languages and tasks indicates improved cross-lingual generalization, suggesting the proposed approach as a practical solution for multilingual consistency alignment under limited supervision.