1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
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.
Paper Type: Long
Research Area: Multilingualism and Cross-Lingual NLP
Research Area Keywords: Multilingual, Large Language Model
Contribution Types: NLP engineering experiment, Approaches to low-resource settings
Languages Studied: English, Chinese
Submission Number: 911
Loading