SOURCE-LINKED INTELLIGENCE

Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Latent language identification is often used to argue that multilingual language models route computation through language-specific states, such as English pivots. However, existing probes infer latent language from different signals, such as the geometry of hidden states or what can be decoded from intermediate representations. Since such claims shape conclusions about how models share and route information across languages, we ask whether these probes measure the same phenomenon or expose distinct aspects of multilingual computation. We study this question across model families, training reg

Read original source ↗ Open in workspace

recordType

paper

region

Global