Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space

Prior research has investigated the impact of various linguistic features on <PRE_TAG>cross-lingual transfer performance</POST_TAG>. In this study, we investigate the manner in which this effect can be mapped onto the representation space. While past studies have focused on the impact on cross-lingual alignment in multilingual language models during fine-tuning, this study examines the absolute evolution of the respective language <PRE_TAG>representation spaces</POST_TAG> produced by MLLMs. We place a specific emphasis on the role of linguistic characteristics and investigate their inter-correlation with the impact on representation spaces and <PRE_TAG>cross-lingual transfer performance</POST_TAG>. Additionally, this paper provides preliminary evidence of how these findings can be leveraged to enhance transfer to linguistically distant languages.