ACL 2023 Multilingual Models Tutorial Slides

The technology landscape is being rapidly transformed by Large Language Models (LLMs), allowing users to address real-world applications in various domains. However, a digital divide exists that may exclude large populations from benefiting and contributing to this technological revolution due to factors such as language, income, digital awareness, and access to information. At Microsoft, we are dedicated to making Large Language Models inclusive to everyone on the planet.

This tutorial will describe various aspects of scaling up language technologies to many of the world’s languages by presenting the latest research in Massively Multilingual Language Models (MMLMs). We will cover topics such as data collection, training and fine-tuning of models, Responsible AI issues such as fairness, bias and toxicity, linguistic diversity and evaluation in the context of MMLMs, specifically focusing on issues in non-English and low-resource languages. Further, we will also talk about some of the real-world challenges in deploying these models in language communities in the field.