Author

Anjelo Jann Laroza

h-index 0 View on Semantic Scholar

2 papers 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 Preprint Sep 2026

FTB Graph: Determining and Validating First-token Broadcasters and Language-Identity Head Circuits in Multilingual Language Models

Large language models operating in multilingual contexts must resolve target response languages early in generation, yet the causal circuitry governing first-token language identity decisions remains poorly mapped. We present an end-to-end structural circuit analysis across six model architectures spanning four familie...

Arjun Pillai, Christian Hoang, A. Laroza · 0 citations

#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