DUAL-REFLECT: Enhancing Large Language Models For Reflective Translation Through Dual Learning Feedback Mechanisms

Chen Andong, Lou Lianzhang, Chen Kehai, Bai Xuefeng, Xiang Yang, Yang Muyun, Zhao Tiejun, Zhang Min. Arxiv 2024

[Paper]    
Applications RAG Tools

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.

Similar Work