基于链式推理的翻译改进：大型语言模型的上下文感知翻译
Chain-of-Thought Reasoning Improves Context-Aware Translation with Large Language Models
AI总结：
本文通过链式推理提升大型语言模型在上下文感知翻译中的表现，发现推理能力显著提高翻译准确率。
摘要：
本文评估了大型语言模型（LLMs）在翻译包含句间依赖关系的文本时的能力。我们使用英语-法语DiscEvalMT基准（Bawden等，2018）中的句子对，这些句子包含翻译挑战，如代词指代和词汇连贯性。我们评估了来自DeepSeek-R1、GPT、Llama、Mistral和Phi家族的12个LLM，在两个任务上：（1）区分正确翻译与看似正确的错误翻译；（2）生成正确翻译。我们比较了鼓励链式推理提示与不鼓励的提示。最佳模型利用推理，在第一个任务上达到约90%的准确率，在第二个任务上获得约92%的COMET分数，其中GPT-4、GPT-4o和Phi表现突出。此外，我们观察到一种“明智者更明智”的效应：通过推理获得的改进在已经无需推理就能表现良好的模型上更为显著。
英文摘要：
This paper assesses the ability of large language models (LLMs) to translate texts that include inter-sentential dependencies. We use the English-French DiscEvalMT benchmark (Bawden et al., 2018) with pairs of sentences containing translation challenges for pronominal anaphora and lexical cohesion. We evaluate 12 LLMs from the DeepSeek-R1, GPT, Llama, Mistral and Phi families on two tasks: (1) distinguish a correct translation from a wrong but plausible one; and (2) generate a correct translation. We compare prompts that encourage chain-of-thought reasoning with those that do not. The best models take advantage of reasoning and reach about 90% accuracy on the first task and COMET scores of about 92% on the second task, with GPT-4, GPT-4o and Phi standing out. Moreover, we observe a "wise get wiser" effect: the improvements through reasoning are larger for models that already perform well without reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
