Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation

ArXi:2604.19678v1 Announce Type: new Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model representations can be language-agnostic, it remains unclear whether the same holds for function vectors. We study whether FVs exhibit language-agnosticity, using machine translation as a.