← Search

Hele-Andra Kuulmets

2 accepted papers

2025

LLMs for Extremely Low-Resource Finno-Ugric Languages

NAACL 2025findings

The advancement of large language models (LLMs) has predominantly focused on high-resource languages, leaving low-resource languages, such as those in the Finno-Ugric family, significantly underrepresented. This paper addresses this gap by focusing on Võro, Livonian, and Komi. We cover almost the en…

2024

Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer

NAACL 2024findings

This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretrainin…