Author

Henrik Sergoyan

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.

#machine learning Preprint Sep 2026

From Zero to Hero: An Open LLM Ecosystem for Armenian

It is found that the largest public Armenian corpora overlap web-derived evaluation panels heavily, including a train/test self-overlap inside FineWeb-2.0, and that a small share of verified translated STEM data reverses the loss.

Erik Arakelyan, Khatun Avetisyan, M. Davtyan et al. · 0 citations