Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?

Yotam Intrator, Matan Halfon, Roman Goldenberg, Reut Tsarfaty, Matan Eyal, Ehud Rivlin, Yossi Matias, Natalia Aizenberg


Abstract
Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating non-English inputs to English before inference, leading to complexity and information loss. This study re-evaluates the need for pre-translation in the context of PaLM2 models, which have been established as highly performant in multilingual tasks. We offer a comprehensive investigation across 108 languages and 6 diverse benchmarks, including open-end generative tasks, which were excluded from previous similar studies. Our findings challenge the pre-translation paradigm established in prior research, highlighting the advantages of direct inference in PaLM2. Specifically, PaLM2-L consistently outperforms pre-translation in 94 out of 108 languages. These findings pave the way for more efficient and effective multilingual applications, alleviating the limitations associated with pre-translation and unlocking linguistic authenticity.
Anthology ID:
2024.naacl-short.75
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
829–844
Language:
URL:
https://aclanthology.org/2024.naacl-short.75
DOI:
10.18653/v1/2024.naacl-short.75
Bibkey:
Cite (ACL):
Yotam Intrator, Matan Halfon, Roman Goldenberg, Reut Tsarfaty, Matan Eyal, Ehud Rivlin, Yossi Matias, and Natalia Aizenberg. 2024. Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications?. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 829–844, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Breaking the Language Barrier: Can Direct Inference Outperform Pre-Translation in Multilingual LLM Applications? (Intrator et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-short.75.pdf