LLM-based Translation Inference with Iterative Bilingual Understanding
This work addresses translation quality degradation for users of LLM-based systems, though it appears incremental as it builds on existing LLM capabilities.
The paper tackled the problem of translation errors caused by incorrect sentence understanding in LLMs by proposing the Iterative Bilingual Understanding Translation (IBUT) method, which uses cross-lingual feedback to iteratively refine contextual understanding, resulting in improved translation performance across multiple domains.
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).