没有万能的方案：从固定提示到学习路由在多语言大语言模型中
No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
AI总结：
研究评估了十种语言和四个基准的提示策略，发现无单一策略最优，提出学习路由方法提升多语言性能。
摘要：
基于翻译的提示在多语言大语言模型中广泛应用，但其效果因语言和任务而异。我们评估了十种语言和四个基准的提示策略，发现没有单一策略普遍最优。翻译对低资源语言有益，即使翻译质量不佳；高资源语言获益有限，提示自路由表现不如显式翻译。受此启发，我们将提示策略选择视为学习决策问题，引入轻量级分类器预测每种实例的最佳原生或翻译提示策略。分类器在四个基准上显著优于固定策略，并泛化到训练未见的任务格式。进一步分析表明，语言资源水平而非翻译质量单独决定翻译是否有益。
英文摘要：
Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.
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。
