Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.13070 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912432172040192 |
|---|---|
| author | Lee, Jaebok Ryu, Yonghyun Park, Seongmin Choi, Yoonjung |
| author_facet | Lee, Jaebok Ryu, Yonghyun Park, Seongmin Choi, Yoonjung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right Lee, Jaebok Ryu, Yonghyun Park, Seongmin Choi, Yoonjung Computation and Language Artificial Intelligence Machine Learning 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. |
| title | CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.13070 |