CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
This work addresses the challenge of accurate named entity translation for machine translation systems, representing an incremental improvement through hybrid methods.
The paper tackles the problem of improving named entity translation accuracy in machine translation by combining Retrieval Augmented Generation (RAG) and iterative self-refinement techniques with LLMs, resulting in enhanced entity handling while maintaining high translation quality.
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.