CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 16 Jun 2025.
Builds on
10 of 20 references.
References · 10
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
- 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
- 2020Autoregressive Entity Retrievalcited by 334
- 2023GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4cited by 146
- 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
- 2023Leveraging GPT-4 for Automatic Translation Post-Editingcited by 56
- 2021DEEP: DEnoising Entity Pre-training for Neural Machine Translationcited by 15
- 2021Generative Relation Linking for Question Answering over Knowledge Basescited by 14
- 2024SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decodingcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Retrieval-Augmented Machine Translation with Unstructured Knowledge
- 2024Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
- 2024Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs
- 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
- 2023Retrieval-Augmented Generation for Large Language Models: A Survey
- 2025Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
- 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
- 2025Tuning LLMs by RAG Principles: Towards LLM-native Memory