“…This generalization capability is further improved with various tuning methods, such as instruction tuning (Sanh et al, 2022;Wei et al, 2022a;Chung et al, 2022;Muennighoff et al, 2022). However, LLMs and their instruction-tuned variants face difficulties in generalizing across various languages, leading to a disparity in performances (Xue et al, 2021;Gehrmann et al, 2022;Scao et al, 2022;Chowdhery et al, 2022;Yong et al, 2023;Zhang et al, 2023;Asai et al, 2023;Kabra et al, 2023). Moreover, these models have limited language coverage, mostly in the Indo-European language family as indicated in Figure 1.…”