用思维令牌生成合成数据，发现对机器翻译帮助不大
LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
- 通过合成思维令牌构建中间推理步骤
- 细调带思维链的模型未优于标准输入输出训练
- 结合模块化提示策略可提升翻译性能
大型推理模型（LRMs）在数学和编程任务中通过自然语言思考过程展现强大解题能力，但在机器翻译（MT）领域的应用仍待探索。本文研究了在多种语言对及不同资源丰富度下，使用中间思维令牌进行翻译的效果。结果表明，单纯添加‘思维令牌’并不能提升模型的翻译表现。这一结论在经过基于人类译者实践的简化思维链（CoT）指导微调后依然成立：用合成的逐步翻译解释微调模型，并未超越标准输入输出微调。然而，若将多个专用于翻译的提示策略输出组合生成中间令牌，则能带来性能提升。研究强调，中间令牌在微调中的有效性高度依赖其是否包含实际翻译尝试。更广泛而言，利用教师模型优化目标翻译或扩充双语语料库，比将思维链解释蒸馏为‘思考型’翻译模型更具影响力。
原文摘要 · Abstract (English)
Large reasoning models (LRMs) have led to new possibilities in terms of problem-solving, through the devising of a natural language thought process prior to answering a query. While their capabilities are well known across mathematics and coding tasks, their impact on the task of machine translation (MT) remains underexplored. In this work, we explore the benefits of the generation of intermediate tokens when performing MT across multiple language pairs of different levels of resourcedness and multiple setups. We find that "thinking tokens" do not help LRMs better perform MT. This result generalizes to models fine-tuned to reason before translating using distilled chain of thought (CoT) inspired by human translators' practices. Specifically, fine-tuning a model with synthetic CoT explanations detailing how to translate step-by-step does not outperform standard input-output fine-tuning. However, constructing the intermediate tokens by combining the outputs of modular translation-specific prompting strategies results in improvements. Our findings underscore that the contribution of intermediate tokens during fine-tuning highly depends on the presence of translation attempts within them. More broadly, our results suggest that using a teacher to refine target translations or to expand parallel corpora is more impactful than distilling their CoT explanations into "thinking" MT models.
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。