About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Andrea Schioppa
- sl:arxiv_num : 2305.11778
- sl:arxiv_published : 2023-05-19T16:14:07Z
- sl:arxiv_summary : The recent rapid progress in pre-training Large Language Models has relied on
using self-supervised language modeling objectives like next token prediction
or span corruption. On the other hand, Machine Translation Systems are mostly
trained using cross-lingual supervision that requires aligned data between
source and target languages. We demonstrate that pre-training Large Language
Models on a mixture of a self-supervised Language Modeling objective and the
supervised Machine Translation objective, therefore including cross-lingual
parallel data during pre-training, yields models with better in-context
learning abilities. As pre-training is a very resource-intensive process and a
grid search on the best mixing ratio between the two objectives is
prohibitively expensive, we propose a simple yet effective strategy to learn it
during pre-training.@en
- sl:arxiv_title : Cross-Lingual Supervision improves Large Language Models Pre-training@en
- sl:arxiv_updated : 2023-05-19T16:14:07Z
- sl:bookmarkOf : https://arxiv.org/abs/2305.11778
- sl:creationDate : 2023-05-22
- sl:creationTime : 2023-05-22T08:13:33Z
Documents with similar tags (experimental)