← all papers · overview

Beyond English-centric Llms: What Language Do Multilingual Language Models Think In?

Abstract

In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to how the representations of intermediate layers, when un-embedded into the vocabulary space, exhibit higher probabilities for certain dominant languages during generation. We term such languages as internal \(\textbf\{late

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).