Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation has mainly focused on better utilizing training data, demonstrations, or pre-defined and universal knowledge to improve performance, with a lack of consideration of decision-making like human translators. In this paper, we incorporate Thinker with the Drift-Diffusion Model (Thinker-DDM) to address this issue. We then redefine the Drift-Diffusion process to emulate human translators' dynamic decision-making under constrained resources. We conduct extensive experiments under the high-resource, low-resource, and commonsense translation settings using the WMT22 and CommonMT datasets, in which Thinker-DDM outperforms baselines in the first two scenarios. We also perform additional analysis and evaluation on commonsense translation to illustrate the high effectiveness and efficacy of the proposed method.

翻译：大型语言模型（LLMs）已在包括机器翻译在内的多项下游任务中展现出显著潜力。然而，现有基于LLM的机器翻译研究主要聚焦于如何更有效地利用训练数据、示例或预定义的通用知识以提升性能，缺乏对类似人类译者的决策过程的考虑。本文提出将思考者与漂移扩散模型（Thinker-DDM）相结合以解决该问题。我们重新定义了漂移扩散过程，以模拟人类译者在资源受限条件下的动态决策机制。基于WMT22和CommonMT数据集，我们在高资源、低资源及常识翻译场景下开展了广泛实验，结果表明Thinker-DDM在前两种场景中优于基线方法。此外，我们针对常识翻译进行了额外分析与评估，验证了所提方法的高效性与有效性。