Cross-Lingual Alignment for Decoder-Only Models using MoE Routers

Excerpt

arXiv:2610.01921v1 Announce Type: cross Abstract: Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible in decoder-only LLMs because of varying multilingual tokenization. However, a growing amount of research suggests that even in LLMs, higher cross-lingual representational alignment leads to improved cross-lingual transfer. In this paper, we propose a novel approach to reimagine cross-li