1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?
This work addresses the challenge of multilingual inconsistency in LLMs, which is an incremental advancement for improving cross-lingual AI applications.
The paper tackles the problem of inconsistent performance of Large Language Models (LLMs) across different languages by introducing a method to aggregate knowledge from diverse languages, resulting in notable improvements, particularly in reducing language performance disparity.
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 language selection process, and mechanisms for answer replacement and integration. Our experiments demonstrate notable performance improvements, particularly in reducing language performance disparity. 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.