1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?

Yue Huang, Chenrui Fan, Yuan Li, Siyuan Wu, Tianyi Zhou, Xiangliang Zhang, Lichao Sun


Abstract
Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for further advancement. This paper introduces a method to enhance the multilingual performance of LLMs by aggregating knowledge from diverse languages. This approach incorporates a low-resource knowledge detector specific to a language, a strategic language selection process, and mechanisms for answer replacement and integration. Our extensive experiments demonstrate notable performance improvements, particularly in reducing the performance disparity across languages. An ablation study confirms that each component of our method significantly contributes to these enhancements. This research highlights the inherent potential of LLMs to harmonize multilingual capabilities and offers valuable insights for further exploration.
Anthology ID:
2024.emnlp-main.743
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:
13394–13412
Language:
URL:
https://aclanthology.org/2024.emnlp-main.743
DOI:
10.18653/v1/2024.emnlp-main.743
Bibkey:
Cite (ACL):
Yue Huang, Chenrui Fan, Yuan Li, Siyuan Wu, Tianyi Zhou, Xiangliang Zhang, and Lichao Sun. 2024. 1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13394–13412, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? (Huang et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.emnlp-main.743.pdf
Software:
 2024.emnlp-main.743.software.zip
Data:
 2024.emnlp-main.743.data.zip