Cross-lingual QA: A Key to Unlocking In-context Cross-lingual Performance
This addresses a cost and efficiency issue for researchers and practitioners using multilingual large language models, but it is incremental as it builds on existing prompting methods.
The paper tackles the problem of high translation costs and contextual integrity loss in cross-lingual in-context learning by introducing Cross-lingual QA, a method that translates only question and answer parts, and shows it outperforms prior monolingual prompting approaches on four multilingual benchmarks.
Multilingual large language models (MLLMs) have demonstrated significant cross-lingual capabilities through in-context learning. Existing approaches typically construct monolingual in-context examples, either in the source or target language. However, translating entire in-context examples into the target language might compromise contextual integrity and be costly in the case of long-context passages. To address this, we introduce Cross-lingual QA, a cross-lingual prompting method that translates only the question and answer parts, thus reducing translation costs. Experiments on four typologically diverse multilingual benchmarks show that Cross-lingual QA prompting effectively stimulates models to elicit their cross-lingual knowledge, outperforming prior monolingual prompting approaches. Furthermore, we show that prompting open-source MLLMs with cross-lingual in-context examples enhances performance as the model scale increases.