Home  | Publications | MLY+25

Exploring the Role of Transliteration in In-Context Learning for Low-Resource Languages Written in Non-Latin Scripts

MCML Authors

Link to Profile Hinrich Schütze PI Matchmaking

Hinrich Schütze

Prof. Dr.

Principal Investigator

Computational Linguistics

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%).

inproceedings

MRL @EMNLP 2025

5th Multilingual Representation Learning Workshop at the Conference on Empirical Methods in Natural Language Processing. Suzhou, China, Nov 04-09, 2025. To be published. Preprint available.

Authors

C. Ma • Y. Liu • H. Ye • H. Schütze

Links

Research Area

 B2 | Natural Language Processing

BibTeXKey: MLY+25

Back to Top