Redefining Machine Translation on Social Network Services with Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912319715409920 |
|---|---|
| author | Guo, Hongcheng Zhao, Fei Cao, Shaosheng Lyu, Xinze Liu, Ziyan Wang, Yue Wang, Boyang Li, Zhoujun Lu, Chonggang Xu, Zhe Hu, Yao |
| author_facet | Guo, Hongcheng Zhao, Fei Cao, Shaosheng Lyu, Xinze Liu, Ziyan Wang, Yue Wang, Boyang Li, Zhoujun Lu, Chonggang Xu, Zhe Hu, Yao |
| contents | The globalization of social interactions has heightened the need for machine translation (MT) on Social Network Services (SNS), yet traditional models struggle with culturally nuanced content like memes, slang, and pop culture references. While large language models (LLMs) have advanced general-purpose translation, their performance on SNS-specific content remains limited due to insufficient specialized training data and evaluation benchmarks. This paper introduces RedTrans, a 72B LLM tailored for SNS translation, trained on a novel dataset developed through three innovations: (1) Supervised Finetuning with Dual-LLM Back-Translation Sampling, an unsupervised sampling method using LLM-based back-translation to select diverse data for large-scale finetuning; (2) Rewritten Preference Optimization (RePO), an algorithm that identifies and corrects erroneous preference pairs through expert annotation, building reliable preference corpora; and (3) RedTrans-Bench, the first benchmark for SNS translation, evaluating phenomena like humor localization, emoji semantics, and meme adaptation. Experiments show RedTrans outperforms state-of-the-art LLMs. Besides, RedTrans has already been deployed in a real-world production environment, demonstrating that domain-specific adaptation, effectively bridges the gap between generic and culturally grounded translation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07901 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Redefining Machine Translation on Social Network Services with Large Language Models Guo, Hongcheng Zhao, Fei Cao, Shaosheng Lyu, Xinze Liu, Ziyan Wang, Yue Wang, Boyang Li, Zhoujun Lu, Chonggang Xu, Zhe Hu, Yao Computation and Language The globalization of social interactions has heightened the need for machine translation (MT) on Social Network Services (SNS), yet traditional models struggle with culturally nuanced content like memes, slang, and pop culture references. While large language models (LLMs) have advanced general-purpose translation, their performance on SNS-specific content remains limited due to insufficient specialized training data and evaluation benchmarks. This paper introduces RedTrans, a 72B LLM tailored for SNS translation, trained on a novel dataset developed through three innovations: (1) Supervised Finetuning with Dual-LLM Back-Translation Sampling, an unsupervised sampling method using LLM-based back-translation to select diverse data for large-scale finetuning; (2) Rewritten Preference Optimization (RePO), an algorithm that identifies and corrects erroneous preference pairs through expert annotation, building reliable preference corpora; and (3) RedTrans-Bench, the first benchmark for SNS translation, evaluating phenomena like humor localization, emoji semantics, and meme adaptation. Experiments show RedTrans outperforms state-of-the-art LLMs. Besides, RedTrans has already been deployed in a real-world production environment, demonstrating that domain-specific adaptation, effectively bridges the gap between generic and culturally grounded translation systems. |
| title | Redefining Machine Translation on Social Network Services with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.07901 |