Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
This work proposes CAROT (Cross-Lingual Alignment of Representations in a Language-Agnostic Space via Optimal Transport), which consists of identifying language-specific representations in LLMs'internal states and aligning language-agnostic representations across languages at the token level by optimal transport, while...
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala et al.
· 0 citations