Author

Ivan Vulic

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.

#natural language process... Apr 2026

Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation

This work systematically characterize what makes an effective multilingual teacher, and combines intrinsic measures of data quality with extrinsic student model performance in a metric the authors call Polyglot Score, which reveals that model scale alone does not significantly predict teacher effectiveness.

Lester James Validad Miranda, Ivan Vulic, Anna Korhonen · arXiv.org · 1 citation

#natural language process... Oct 2025

Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models

This work conducts the first large-scale, systematic studies of multilingual calibration across six model families and over 100 languages, revealing that non-English languages suffer from systematically worse calibration.

Ej Zhou, Caiqi Zhang, Tiancheng Hu et al. · arXiv.org · 10 citations · ⚡1