人设是一把双刃剑：缓解零样本推理任务中角色扮演提示的负面影响
Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
AI总结：
本文研究角色扮演提示对LLM零样本推理的负面影响，并提出Jekyll & Hyde框架，通过集成角色扮演与中性提示结果并由LLM评估选择更优解，在12个推理数据集上提升推理鲁棒性。
摘要：
近期研究表明，向大语言模型（LLM）提示一个角色扮演人设可以提升推理能力。然而，分配一个合适的人设十分困难，因为LLM对指定的提示极其敏感；因此，定义不准确的人设有时会妨碍LLM并降低其推理能力。在本文中，我们首先研究了将人设注入语言模型可能带来的负面影响。此外，我们提出了一个新的框架Jekyll & Hyde，该框架集成角色扮演提示和中性提示的结果，以增强推理能力的鲁棒性。具体来说，Jekyll & Hyde在定义角色扮演提示时，利用LLM预测一个合适的人设。然后，Jekyll & Hyde分别从角色扮演提示和中性提示中收集两个潜在解，并使用LLM评估器选择更优的解。实验分析表明，角色扮演提示有时会分散LLM的注意力，在llama3的12个数据集中有7个数据集上降低了推理能力。同时，Jekyll & Hyde通过在12个广泛使用的自然语言推理数据集上从潜在解中选择更优答案，提升了推理能力。此外，我们还发现，分配由LLM生成的人设比手工设计的人设能获得更稳定的结果。
英文摘要：
Recent studies demonstrate that prompting a role-playing persona to an LLM improves reasoning capability. However, assigning an adequate persona is difficult since LLMs are extremely sensitive to assigned prompts; thus, inaccurately defined personas sometimes hinder LLMs and degrade their reasoning capabilities. In this paper, we first investigate the potential negative impact of injecting persona into language models. Furthermore, we propose a novel framework, Jekyll \& Hyde, which ensembles the outcomes of both role-playing and neutral prompts to enhance the robustness of reasoning ability. Specifically, Jekyll \& Hyde predicts an appropriate persona using an LLM when defining the role-playing prompt. Then, Jekyll \& Hyde collects two potential solutions from role-playing and neutral prompts and selects a better solution using the LLM evaluator. The experimental analysis demonstrates that role-playing prompts sometimes distract LLMs, degrading their reasoning abilities in 7 out of 12 datasets in llama3. Meanwhile, Jekyll \& Hyde improve reasoning capabilities by selecting better choices among the potential solutions on twelve widely-used natural language reasoning datasets. In addition, we reveal that assigning LLM-generated personas obtains more stable results than handcrafted personas.
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。
