DUAL-REFLECT：通过对偶学习反馈机制增强大语言模型的反思式翻译能力
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
AI总结：
针对现有大语言模型自反思翻译方法缺乏有效反馈的问题，提出DUAL-REFLECT框架，借助翻译任务对偶学习提供反馈以增强自反思能力，可提升翻译准确率、消除歧义，在低资源语言对翻译中效果显著。
摘要：
近年来，经自反思增强的大语言模型（LLMs）在机器翻译任务上取得了可观的性能表现，其核心思路是引导LLMs借助类人反馈生成译文。然而，现有自反思方法缺乏有效的反馈信息，制约了翻译性能。为解决这一问题，我们提出DUAL-REFLECT框架，利用翻译任务的对偶学习提供有效反馈，以此增强模型的自反思能力、提升翻译性能。该方法在多类翻译任务中的应用证实，其能有效提升翻译准确率、消除歧义，在低资源语言对的翻译任务中效果尤为突出。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
