发表机构
School of Informatics, Xiamen University; Tongyi Lab; The Chinese University of Hong Kong; Soochow University（厦门大学信息学院; 通义实验室; 香港中文大学; 苏州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过多模型跨语言实验发现角色扮演提示的效果依赖模型能力与领域，提出认知对齐假说及MLCP策略，无需训练即可稳定提升推理性能。
AI 中文摘要
角色扮演提示已成为一种流行且简单的技术，用于提升大型语言模型的推理能力和输出质量。然而，它在不同领域是否始终如一地提升性能仍不清楚，因为缺乏系统性的验证。为了填补这一空白，我们在MMLU和MMLU-Redux上进行了多模型、跨领域和多语言的实验。我们发现，角色扮演提示带来的增益在很大程度上取决于模型能力、知识领域和提示语言。借鉴元认知理论，我们提出了与角色相关的认知对齐假说：只有当大型语言模型正确把握指定角色及其相关知识领域时，角色扮演才有效。我们通过角色信息丰富度消融、逐层熵散度分析和潜在思维空间偏转观察来检验这一假说。为了减少角色认知偏差并稳定角色扮演性能，我们提出了混合语言拼接预测（MLCP），这是一种简单、无需训练且高效的多语言提示拼接策略。它聚合语义等效的角色提示，以丰富互补的表征线索。大量实验表明，MLCP在所有测试的大型语言模型上始终优于原始的角色扮演提示。
英文摘要
Role-playing prompting has become a popular yet simple technique for improving LLM reasoning and output quality. However, whether it consistently boosts performance across diverse domains remains unclear, as systematic validation is lacking. To fill this gap, we run multi-model, cross-domain, and multilingual experiments on MMLU and MMLU-Redux. We find that gains from role-play prompting depend heavily on model capacity, knowledge domain, and prompt language. Drawing on metacognition theory, we propose the persona-related cognitive alignment hypothesis: role-play works only when the LLM correctly grasps the designated persona and its associated knowledge domain. We test this hypothesis through persona information richness ablation, layer-wise entropy divergence analysis, and latent thought-space deflection observation. To reduce persona cognitive bias and stabilize role-play performance, we propose \textbf{M}ixed-\textbf{L}anguage \textbf{C}oncatenate \textbf{P}rediction \textbf{(MLCP}), a simple, training-free, and efficient multilingual prompt concatenation strategy. It aggregates semantically equivalent role prompts to enrich complementary representational cues. Extensive experiments show that MLCP consistently outperforms vanilla role-play prompting across all tested LLMs.
Comments22 pages, 7 figures
