Paraphrase-Aligned Machine Translation
This addresses translation quality issues for users of LLMs, but it is incremental as it builds on existing fine-tuning methods.
The paper tackles the problem of LLM-generated translations deviating from native speaker expressions by proposing ParaAlign Translator, which fine-tunes LLMs to paraphrase sentences for better alignment with target language structures, resulting in improved performance for the LLaMA-3-8B model that matches or surpasses the larger LLaMA-3-70B model.
Large Language Models (LLMs) have demonstrated significant capabilities in machine translation. However, their translation quality is sometimes questioned, as the generated outputs may deviate from expressions typically used by native speakers. These deviations often arise from differences in sentence structure between language systems. To address this issue, we propose ParaAlign Translator, a method that fine-tunes LLMs to paraphrase sentences, aligning their structures with those of the target language systems. This approach improves the performance of subsequent translations. Experimental results demonstrate that the proposed method enhances the LLaMA-3-8B model's performance in both resource-rich and low-resource scenarios and achieves parity with or surpassing the much larger LLaMA-3-70B model.