解决大模型多语言性能不均问题，提升非英语表现
Aligning LLMs for Multilingual Consistency in Enterprise Applications
- 用同义多语言数据批量对齐模型输出，实现跨语言一致性
- 非英语准确率最高提升23.9%，英语性能不变
- 方法简单可扩展，适合企业级多语言AI部署
大语言模型在跨国企业应用中仍不可靠，因高资源语言与中/低资源语言间存在显著性能差距，根源在于以英语为中心的预训练和内部推理偏见。这种不一致性削弱了客户支持、内容审核和信息检索等多语言场景下的用户体验与运营可靠性。即使采用先进的检索增强生成（RAG）系统，非英语语言的准确率仍比英语低最多29%。本文提出一种实用的批量对齐微调策略，利用每个训练批次中的语义等价多语言数据，直接对齐模型在不同语言间的输出。该方法使非英语准确率提升最高达23.9%，且不影响英语性能、模型推理能力或检索质量。该方法易于实现、可扩展，能无缝集成至现有大模型训练与部署流程，助力产业界构建更稳健、更公平的多语言AI解决方案。
原文摘要 · Abstract (English)
Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases. This inconsistency undermines customer experience and operational reliability in multilingual settings such as customer support, content moderation, and information retrieval. Even with advanced Retrieval-Augmented Generation (RAG) systems, we observe up to an 29% accuracy drop in non-English languages compared to English. We propose a practical, batch-wise alignment strategy for fine-tuning LLMs, leveraging semantically equivalent multilingual data in each training batch to directly align model outputs across languages. This approach improves non-English accuracy by up to 23.9% without compromising English performance, model reasoning, or retrieval quality. Our method is simple to implement, scalable, and integrates seamlessly with existing LLM training & deployment pipelines, enabling more robust and equitable multilingual AI solutions in industry.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。