用提示词迭代优化翻译，让大模型更准地处理冷门词。
Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
- 先找关键术语，从双语词典查译法，用RAG注入上下文
- 通过多轮自检减少幻觉，翻译准确率在低资源场景提升显著
- 适合需要高保真翻译的领域，如医学、法律等专业文本
大语言模型在机器翻译中表现优异，但对低资源或特定领域的罕见词汇仍存在挑战。为此，我们提出一种多步提示链方法：首先识别关键术语，并从双语词典中检索其译法，通过检索增强生成（RAG）将其融入模型上下文；再通过迭代自检机制，依据词汇与语义约束修正输出，缓解长提示带来的幻觉问题。在FLORES-200和WMT数据集上，以Llama和Qwen为基模型的实验表明，该方法显著优于基线，在低资源场景下有效提升了翻译的忠实度与鲁棒性。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT), even without specific training on the languages in question. However, translating rare words in low-resource or domain-specific contexts remains challenging for LLMs. To address this issue, we propose a multi-step prompt chain that enhances translation faithfulness by prioritizing key terms crucial for semantic accuracy. Our method first identifies these keywords and retrieves their translations from a bilingual dictionary, integrating them into the LLM's context using Retrieval-Augmented Generation (RAG). We further mitigate potential output hallucinations caused by long prompts through an iterative self-checking mechanism, where the LLM refines its translations based on lexical and semantic constraints. Experiments using Llama and Qwen as base models on the FLORES-200 and WMT datasets demonstrate significant improvements over baselines, highlighting the effectiveness of our approach in enhancing translation faithfulness and robustness, particularly in low-resource scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。