LLM-based Translation Inference with Iterative Bilingual Understanding
Andong Chen, Kehai Chen, Yang Xiang, Xuefeng Bai, Muyun Yang, Yang Feng, Tiejun Zhao, Min Zhang
Abstract
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).
BibTeX
@inproceedings{chen-etal-2025-llm-based,
title = "{LLM}-based Translation Inference with Iterative Bilingual Understanding",
author = "Chen, Andong and
Chen, Kehai and
Xiang, Yang and
Bai, Xuefeng and
Yang, Muyun and
Feng, Yang and
Zhao, Tiejun and
Zhang, Min",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.867/",
doi = "10.18653/v1/2025.findings-acl.867",
pages = "16886--16902",
ISBN = "979-8-89176-256-5"
}