Publications

Preprints

arXiv, 2026

Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning

Preprint on multilingual code-switching in instruction tuning.

View publication

Conference and Workshop Papers

ICLR 2026 Workshop DATA-FM

Beyond Training for Cultural Awareness: The Role of Dataset Linguistic Structure in Large Language Models

Non-archival workshop paper at ICLR 2026 Workshop on Navigating and Addressing Data Problems for Foundation Models (DATA-FM).

View publication · arXiv:2602.01161