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.
BibTeX
@inproceedings{huang-etal-2024-1,
title = "1+1{\ensuremath{>}}2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?",
author = "Huang, Yue and
Fan, Chenrui and
Li, Yuan and
Wu, Siyuan and
Zhou, Tianyi and
Zhang, Xiangliang and
Sun, Lichao",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.743/",
doi = "10.18653/v1/2024.emnlp-main.743",
pages = "13394--13412"
}