Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks

TL;DR

This survey reviews recent advancements in multilingual prompt engineering for large language models, highlighting techniques, datasets, and insights across diverse languages and NLP tasks to improve model performance without extensive retraining.

Contribution

It categorizes and analyzes 36 papers and 39 prompting techniques across 250 languages, providing a comprehensive taxonomy and insights into multilingual prompt engineering.

Findings

Effective prompts improve LLM performance across languages

Techniques vary by language resource level and family

Recent studies focus on low-resource languages

Abstract

Large language models (LLMs) have demonstrated impressive performance across a wide range of Natural Language Processing (NLP) tasks. However, ensuring their effectiveness across multiple languages presents unique challenges. Multilingual prompt engineering has emerged as a key approach to enhance LLMs' capabilities in diverse linguistic settings without requiring extensive parameter re-training or fine-tuning. With growing interest in multilingual prompt engineering over the past two to three years, researchers have explored various strategies to improve LLMs' performance across languages and NLP tasks. By crafting structured natural language prompts, researchers have successfully extracted knowledge from LLMs across different languages, making these techniques an accessible pathway for a broader audience, including those without deep expertise in machine learning, to harness the capabilities of LLMs. In this paper, we survey and categorize different multilingual prompting techniques based on the NLP tasks they address across a diverse set of datasets that collectively span around 250 languages. We further highlight the LLMs employed, present a taxonomy of approaches and discuss potential state-of-the-art (SoTA) methods for specific multilingual datasets. Additionally, we derive a range of insights across language families and resource levels (high-resource vs. low-resource), including analyses such as the distribution of NLP tasks by language resource type and the frequency of prompting methods across different language families. Our survey reviews 36 research papers covering 39 prompting techniques applied to 30 multilingual NLP tasks, with the majority of these studies published in the last two years.