Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection methods lack effective feedback information, limiting the translation performance. To address this, we introduce a DUAL-REFLECT framework, leveraging the dual learning of translation tasks to provide effective feedback, thereby enhancing the models' self-reflective abilities and improving translation performance. The application of this method across various translation tasks has proven its effectiveness in improving translation accuracy and eliminating ambiguities, especially in translation tasks with low-resource language pairs.
@article{arxiv.2406.07232,
title = {DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms},
author = {Andong Chen and Lianzhang Lou and Kehai Chen and Xuefeng Bai and Yang Xiang and Muyun Yang and Tiejun Zhao and Min Zhang},
journal= {arXiv preprint arXiv:2406.07232},
year = {2024}
}