Saved in:
Bibliographic Details
Main Authors: Bakkenes, Tim, Wang, Daniel, Johansson, Anton
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.04139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908577228128256
author Bakkenes, Tim
Wang, Daniel
Johansson, Anton
author_facet Bakkenes, Tim
Wang, Daniel
Johansson, Anton
contents The rise of Large Language Models has not been inclusive of all cultures. The models are mostly trained on English texts and culture which makes them underperform in other languages and cultural contexts. By developing a generalizable method for preparing culturally relevant datasets and post-training the Gemma 2 model, this project aimed to increase the performance of Gemma 2 for an underrepresented language and showcase how others can do the same to unlock the power of Generative AI in their country and preserve their cultural heritage.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fine Tuning Methods for Low-resource Languages
Bakkenes, Tim
Wang, Daniel
Johansson, Anton
Computation and Language
Machine Learning
The rise of Large Language Models has not been inclusive of all cultures. The models are mostly trained on English texts and culture which makes them underperform in other languages and cultural contexts. By developing a generalizable method for preparing culturally relevant datasets and post-training the Gemma 2 model, this project aimed to increase the performance of Gemma 2 for an underrepresented language and showcase how others can do the same to unlock the power of Generative AI in their country and preserve their cultural heritage.
title Fine Tuning Methods for Low-resource Languages
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2510.04139