A Survey of Large Language Models for European Languages

TL;DR

This survey reviews large language models focusing on European languages, covering their development, datasets, and methods, highlighting recent advancements and challenges in multilingual NLP for EU languages.

Contribution

It provides a comprehensive overview of LLMs, datasets, and techniques specifically tailored for European languages, filling a gap in current multilingual NLP research.

Findings

Summarizes major LLM families like LLaMA, GPT, PaLM, MoE.

Details datasets used for pretraining European language models.

Highlights recent methods for improving LLMs in EU languages.

Abstract

Large Language Models (LLMs) have gained significant attention due to their high performance on a wide range of natural language tasks since the release of ChatGPT. The LLMs learn to understand and generate language by training billions of model parameters on vast volumes of text data. Despite being a relatively new field, LLM research is rapidly advancing in various directions. In this paper, we present an overview of LLM families, including LLaMA, PaLM, GPT, and MoE, and the methods developed to create and enhance LLMs for official European Union (EU) languages. We provide a comprehensive summary of common monolingual and multilingual datasets used for pretraining large language models.