Lost in Translation: Large Language Models in Non-English Content Analysis

TL;DR

This paper examines the capabilities, limitations, and challenges of multilingual large language models in processing non-English content, highlighting data gaps and offering recommendations for responsible deployment.

Contribution

It provides a comprehensive explanation of how multilingual models work, analyzes their limitations, and offers practical guidance for stakeholders involved in their development and use.

Findings

Multilingual models perform less effectively in non-English languages due to data scarcity.

Challenges include understanding cultural context and content moderation complexities.

Recommendations focus on data diversity, transparency, and ethical considerations.

Abstract

In recent years, large language models (e.g., Open AI's GPT-4, Meta's LLaMa, Google's PaLM) have become the dominant approach for building AI systems to analyze and generate language online. However, the automated systems that increasingly mediate our interactions online -- such as chatbots, content moderation systems, and search engines -- are primarily designed for and work far more effectively in English than in the world's other 7,000 languages. Recently, researchers and technology companies have attempted to extend the capabilities of large language models into languages other than English by building what are called multilingual language models. In this paper, we explain how these multilingual language models work and explore their capabilities and limits. Part I provides a simple technical explanation of how large language models work, why there is a gap in available data between English and other languages, and how multilingual language models attempt to bridge that gap. Part II accounts for the challenges of doing content analysis with large language models in general and multilingual language models in particular. Part III offers recommendations for companies, researchers, and policymakers to keep in mind when considering researching, developing and deploying large and multilingual language models.