SOURCE-LINKED INTELLIGENCE

Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Cross-lingual alignment (CLA) aims to align the representations of large language models (LLMs) across languages, enabling cross-lingual transfer to improve multilingual capabilities. Previous CLA methods often ignore language-specific information encoded in representations and only consider sentence-level alignment, which may lead to suboptimal performance and input-output language mismatch. We propose CAROT (Cross-Lingual Alignment of Representations in a Language-Agnostic Space via Optimal Transport), which consists of two steps: identifying language-specific representations in LLMs' intern

Read original source ↗ Open in workspace

recordType

paper

region

Global