SAGE：面向文化适应翻译的可持续代理引导专家调优
SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia
AI总结：
SAGE通过能量感知方法优化低资源东南亚地区翻译任务，利用强化学习代理筛选高质量数据，显著降低能耗和数据使用量，提升模型性能与环保性。
摘要：
包容性的万维网愿景受严重语言障碍阻碍，尤其在低资源东南亚地区。尽管大语言模型（LLMs）为翻译提供了潜在解决方案，但在数据贫乏环境中面临双重挑战：高质量、文化相关数据稀缺和大规模噪声网络语料训练的高能耗。为解决数字包容与环境可持续性的矛盾，我们引入可持续代理引导专家调优（SAGE）。该框架开创了一种以'正确数据'优先于'大数据'的能源感知范式。SAGE采用强化学习（RL）代理，通过组相对策略优化（GRPO）进行优化，自主筛选紧凑训练集。代理利用来自小规模专家构建社区对话的语义奖励信号来过滤噪声和文化不匹配。然后使用低秩适应（LoRA）高效微调开源LLMs。我们应用SAGE于英语与七个低资源语言（LRLs）之间的翻译任务。我们的方法在BLEU-4和COMET-22指标上建立了新的最先进性能，有效捕捉本地语言细微差别。关键的是，SAGE在训练完整数据集的基线基础上，减少了97.1%的数据使用量和95.2%的训练能耗。通过提供高性能模型的同时最小化环境足迹，SAGE为全球南方的数字鸿沟提供了可扩展且负责任的解决方案。
英文摘要：
The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their deployment in data-poor contexts faces a dual challenge: the scarcity of high-quality, culturally relevant data and the prohibitive energy costs of training on massive, noisy web corpora. To resolve the tension between digital inclusion and environmental sustainability, we introduce Sustainable Agent-Guided Expert-tuning (SAGE). This framework pioneers an energy-aware paradigm that prioritizes the "right data" over "big data". Instead of carbon-intensive training on unfiltered datasets, SAGE employs a reinforcement learning (RL) agent, optimized via Group Relative Policy Optimization (GRPO), to autonomously curate a compact training set. The agent utilizes a semantic reward signal derived from a small, expert-constructed set of community dialogues to filter out noise and cultural misalignment. We then efficiently fine-tune open-source LLMs on this curated data using Low-Rank Adaptation (LoRA). We applied SAGE to translation tasks between English and seven low-resource languages (LRLs) in Southeast Asia. Our approach establishes new state-of-the-art performance on BLEU-4 and COMET-22 metrics, effectively capturing local linguistic nuances. Crucially, SAGE surpasses baselines trained on full datasets while reducing data usage by 97.1% and training energy consumption by 95.2%. By delivering high-performance models with a minimal environmental footprint, SAGE offers a scalable and responsible pathway to bridge the digital divide in the Global South.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
