Prompting Large Language Model for Machine Translation: A Case Study

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Research on prompting has shown excellent performance with little or even no supervised training across many tasks. However, prompting for machine translation is still under-explored in the literature. We fill this gap by offering a systematic study on prompting strategies for translation, examining various factors for prompt template and demonstration example selection. We further explore the use of monolingual data and the feasibility of cross-lingual, cross-domain, and sentence-to-document transfer learning in prompting. Extensive experiments with GLM-130B (Zeng et al., 2022) as the testbed show that 1) the number and the quality of prompt examples matter, where using suboptimal examples degenerates translation; 2) several features of prompt examples, such as semantic similarity, show significant Spearman correlation with their prompting performance; yet, none of the correlations are strong enough; 3) using pseudo parallel prompt examples constructed from monolingual data via zero-shot prompting could improve translation; and 4) improved performance is achievable by transferring knowledge from prompt examples selected in other settings. We finally provide an analysis on the model outputs and discuss several problems that prompting still suffers from.
Original languageEnglish
Title of host publicationProceedings of the 40th International Conference on Machine Learning
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
Number of pages19
Publication statusPublished - 1 Nov 2023
EventThe Fortieth International Conference on Machine Learning - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
Conference number: 40

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


ConferenceThe Fortieth International Conference on Machine Learning
Abbreviated titleICML 2023
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Prompting Large Language Model for Machine Translation: A Case Study'. Together they form a unique fingerprint.

Cite this