Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts
Abstract: Decoder-only large language models (LLMs) excel in high-resource languages across various tasks through few-shot or even zero-shot in-context learning (ICL). However, their performance often does not transfer well to low-resource languages, especially those written in non-Latin scripts. Inspired by recent work that leverages transliteration in encoder-only models, we investigate whether transliteration is also effective in improving LLMs' performance for low-resource languages written in non-Latin scripts. To this end, we propose three prompt templates, where the target-language text is represented in (1) its original script, (2) Latin script, or (3) both. We apply these methods to several representative LLMs of different sizes on various tasks including text classification and sequential labeling. Our findings show that the effectiveness of transliteration varies by task type and model size. For instance, all models benefit from transliterations for sequential labeling (with increases of up to 25%). We make our code publicly available.
Paper Type: Short
Research Area: Multilingualism and Cross-Lingual NLP
Research Area Keywords: multilingualism, multilingual evaluation, less-resourced languages, transliteration, LLM
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings
Languages Studied: We evaluate on three datasets where each covers more than 60 languages.
Submission Number: 1463
Loading