Author

Christian Hoang

View on Semantic Scholar

1 paper indexed here

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 Jun 2026

First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers

Extended experiments with Chinese and Russian confirm that first-token broadcasting is script-specific in GPT-2, with non-Latin languages handled at layer 0 - the same locus as the instruction-tuned model.

Arjun Pillai, Christian Hoang, Anjelo Jann Laroza · arXiv.org · 0 citations