SOURCE-LINKED INTELLIGENCE

Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Multilingual large language models (mLLMs) achieve strong performance in machine translation, yet our understanding of the mechanisms by which they transform representations from one language to another remains incomplete. Prior work suggests that translation decomposes into separable processes within an mLLM, where conceptual content is first represented independently, followed by a production into language-specific form. In this work, we show that translation is even more modular than previously assumed and that the output language production in translation processes is actually further sepa

Read original source ↗ Open in workspace

recordType

paper

region

Global