Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages

TL;DR

This paper proposes Chain of Translation Prompting (CoTR), a new method that improves language model performance on low-resource languages by translating inputs to high-resource languages, performing tasks, and optionally translating outputs back, demonstrated on Marathi.

Contribution

Introduces CoTR, a novel prompt design that leverages translation to enhance NLP task performance in low-resource languages, with empirical validation on Marathi.

Findings

Significant accuracy improvements in hate speech detection

Effective across multiple NLP tasks including sentiment and subject classification

Potential to improve synthetic data quality for underrepresented languages

Abstract

This paper introduces Chain of Translation Prompting (CoTR), a novel strategy designed to enhance the performance of language models in low-resource languages. CoTR restructures prompts to first translate the input context from a low-resource language into a higher-resource language, such as English. The specified task like generation, classification, or any other NLP function is then performed on the translated text, with the option to translate the output back to the original language if needed. All these steps are specified in a single prompt. We demonstrate the effectiveness of this method through a case study on the low-resource Indic language Marathi. The CoTR strategy is applied to various tasks, including sentiment analysis, hate speech classification, subject classification and text generation, and its efficacy is showcased by comparing it with regular prompting methods. Our results underscore the potential of translation-based prompting strategies to significantly improve multilingual LLM performance in low-resource languages, offering valuable insights for future research and applications. We specifically see the highest accuracy improvements with the hate speech detection task. The technique also has the potential to enhance the quality of synthetic data generation for underrepresented languages using LLMs.