超越英語：邁向基於大型語言模型的包容性與可擴展多語言機器翻譯

摘要

大型語言模型顯著推進了多語言機器翻譯（MMT）的發展，然而廣泛的語言覆蓋範圍、一致的翻譯品質以及以英語為中心的偏差仍是待解決的挑戰。為應對這些挑戰，我們推出LMT——一套以中英雙語為核心的大規模多語言翻譯模型，涵蓋60種語言及234個翻譯方向。在開發過程中，我們發現了先前被忽略的「方向性退化」現象：對稱多向微調數據過度側重反向翻譯（X→英/中），導致過多的多對一映射並降低翻譯品質。為此提出「策略性降採樣」這一簡潔有效的方法來緩解此類退化。此外，我們設計了平行多語言提示（PMP）機制，利用類型學相關的輔助語言增強跨語言遷移能力。通過嚴格的數據篩選與優化的適應策略，LMT在同等語言覆蓋規模的模型中實現了最優性能，其中40億參數模型（LMT-60-4B）更以顯著優勢超越參數規模更大的Aya-101-13B和NLLB-54B模型。我們發布四種規模的LMT模型（6億/17億/40億/80億）以促進未來研究，並為實現包容性、可擴展且高品質的MMT提供強力基準\href{https://github.com/NiuTrans/LMT}{https://github.com/NiuTrans/LMT}。

English

Large language models have significantly advanced Multilingual Machine Translation (MMT), yet the broad language coverage, consistent translation quality, and English-centric bias remain open challenges. To address these challenges, we introduce LMT, a suite of Large-scale Multilingual Translation models centered on both Chinese and English, covering 60 languages and 234 translation directions. During development, we identify a previously overlooked phenomenon of directional degeneration, where symmetric multi-way fine-tuning data overemphasize reverse directions (X to En/Zh), leading to excessive many-to-one mappings and degraded translation quality. We propose Strategic Downsampling, a simple yet effective method to mitigate this degeneration. In addition, we design Parallel Multilingual Prompting (PMP), which leverages typologically related auxiliary languages to enhance cross-lingual transfer. Through rigorous data curation and refined adaptation strategies, LMT achieves SOTA performance among models of comparable language coverage, with our 4B model (LMT-60-4B) surpassing the much larger Aya-101-13B and NLLB-54B models by a substantial margin. We release LMT in four sizes (0.6B/1.7B/4B/8B) to catalyze future research and provide strong baselines for inclusive, scalable, and high-quality MMT \href{https://github.com/NiuTrans/LMT{https://github.com/NiuTrans/LMT}}.

超越英語：邁向基於大型語言模型的包容性與可擴展多語言機器翻譯

Beyond English: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs

摘要

Support