用自检机制让大模型精准翻译专有名词。
CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
- 结合检索增强与迭代自修正提升实体翻译
- 自评机制确保实体准确率与整体质量双高
- 适合关注跨语言实体对齐的研究者
本文介绍了我们在 SemEval 2025 任务 2（实体感知机器翻译，EA-MT）中的方法。系统通过融合检索增强生成（RAG）与基于大语言模型（LLM）的迭代自修正技术，提升命名实体翻译的准确性。其独特之处在于引入了自评估机制，由 LLM 根据实体翻译准确性和整体翻译质量双重标准自我评判。实验表明，该方法有效提升了实体处理能力，同时保持了高质量的翻译输出。
原文摘要 · Abstract (English)
In this paper, we describe our approach for the SemEval 2025 Task 2 on Entity-Aware Machine Translation (EA-MT). Our system aims to improve the accuracy of translating named entities by combining two key approaches: Retrieval Augmented Generation (RAG) and iterative self-refinement techniques using Large Language Models (LLMs). A distinctive feature of our system is its self-evaluation mechanism, where the LLM assesses its own translations based on two key criteria: the accuracy of entity translations and overall translation quality. We demonstrate how these methods work together and effectively improve entity handling while maintaining high-quality translations.
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。