現代機器翻譯的新趨勢：基於大型推理模型

New Trends for Modern Machine Translation with Large Reasoning Models

March 13, 2025

作者: Sinuo Liu, Chenyang Lyu, Minghao Wu, Longyue Wang, Weihua Luo, Kaifu Zhang

cs.AI

摘要

大型推理模型（LRMs）的最新進展，尤其是那些利用思維鏈推理（CoT）的模型，為機器翻譯（MT）開闢了全新的可能性。本立場文件主張，LRMs通過將翻譯重新定義為一項需要上下文、文化和語言理解與推理的動態推理任務，從根本上轉變了傳統神經機器翻譯以及基於大型語言模型（LLMs）的翻譯範式。我們識別出三大基礎性轉變：1）上下文連貫性，LRMs通過對跨句子和複雜上下文甚至缺乏上下文的顯式推理來解決歧義並保持話語結構；2）文化意圖性，使模型能夠通過推斷說話者意圖、受眾期望和社會語言規範來調整輸出；3）自我反思，LRMs能夠在推理過程中進行自我反思，以糾正翻譯中的潛在錯誤，特別是在極端噪聲情況下，相比於簡單的X->Y映射翻譯，展現出更好的魯棒性。我們通過展示實證案例，探討了翻譯中的各種場景，包括風格化翻譯、文檔級翻譯和多模態翻譯，這些案例展示了LRMs在翻譯中的優越性。我們還識別了LRMs在機器翻譯中的幾個有趣現象，如自動樞紐翻譯，以及關鍵挑戰，如翻譯中的過度本地化和推理效率。總之，我們認為LRMs重新定義了翻譯系統，使其不僅僅是文本轉換器，而是能夠推理文本之外意義的多語言認知代理。這一範式轉變提醒我們，在更廣泛的背景下，利用LRMs思考翻譯問題——我們在此基礎上能實現什麼。

English

Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms by reframing translation as a dynamic reasoning task that requires contextual, cultural, and linguistic understanding and reasoning. We identify three foundational shifts: 1) contextual coherence, where LRMs resolve ambiguities and preserve discourse structure through explicit reasoning over cross-sentence and complex context or even lack of context; 2) cultural intentionality, enabling models to adapt outputs by inferring speaker intent, audience expectations, and socio-linguistic norms; 3) self-reflection, LRMs can perform self-reflection during the inference time to correct the potential errors in translation especially extremely noisy cases, showing better robustness compared to simply mapping X->Y translation. We explore various scenarios in translation including stylized translation, document-level translation and multimodal translation by showcasing empirical examples that demonstrate the superiority of LRMs in translation. We also identify several interesting phenomenons for LRMs for MT including auto-pivot translation as well as the critical challenges such as over-localisation in translation and inference efficiency. In conclusion, we think that LRMs redefine translation systems not merely as text converters but as multilingual cognitive agents capable of reasoning about meaning beyond the text. This paradigm shift reminds us to think of problems in translation beyond traditional translation scenarios in a much broader context with LRMs - what we can achieve on top of it.