[go: up one dir, main page]

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?

Pinzhen Chen, Simon Yu, Zhicheng Guo, Barry Haddow


Abstract
Multilingual large language models are designed, claimed, and expected to cater to speakers of varied languages. We hypothesise that the current practices of fine-tuning and evaluating these models may not perfectly align with this objective owing to a heavy reliance on translation, which cannot cover language-specific knowledge but can introduce translation defects. It remains unknown whether the nature of the instruction data has an impact on the model output; conversely, it is questionable whether translated test sets can capture such nuances. Due to the often coupled practices of using translated data in both stages, such imperfections could have been overlooked. This work investigates these issues using controlled native or translated data during the instruction tuning and evaluation stages. We show that native or generation benchmarks reveal a notable difference between native and translated instruction data especially when model performance is high, whereas other types of test sets cannot. The comparison between round-trip and single-pass translations reflects the importance of knowledge from language-native resources. Finally, we demonstrate that regularization is beneficial to bridging this gap on structured but not generative tasks.
Anthology ID:
2024.emnlp-main.542
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9706–9726
Language:
URL:
https://aclanthology.org/2024.emnlp-main.542
DOI:
10.18653/v1/2024.emnlp-main.542
Bibkey:
Cite (ACL):
Pinzhen Chen, Simon Yu, Zhicheng Guo, and Barry Haddow. 2024. Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9706–9726, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models? (Chen et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.542.pdf