Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.08348 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917835903598592 |
|---|---|
| author | Chen, Shangfeng Shi, Xiayang Li, Pu Li, Yinlin Liu, Jingjing |
| author_facet | Chen, Shangfeng Shi, Xiayang Li, Pu Li, Yinlin Liu, Jingjing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08348 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach Chen, Shangfeng Shi, Xiayang Li, Pu Li, Yinlin Liu, Jingjing Computation and Language 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. |
| title | Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.08348 |