Author

Deniz Bayazit

EPFL NLP

h-index 7 Homepage View on Semantic Scholar

We have 1 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

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

This work finds that identification probes systematically disagree: the GMM-based representation probe, which draws evidence from hidden state geometry, shows earlier cross-lingual mixing, whereas decoding-based probes, which rely on output-space decodability, retain sharper language-specific and more English-biased si...

Deniz Bayazit, Badr AlKhamissi, Antoine Bosselut · 0 citations