动态切换提示策略，让大模型推理更稳定可靠。
Persona Switch: Mixing Distinct Perspectives in Decoding Time
- 每步决策时比较零样本与角色扮演提示的置信度，择优选择。
- 在多个任务上提升准确率，最高达5.13%。
- 适合需要高可靠性的对话生成与复杂推理场景。
角色扮演提示通过在提示中注入人格特征，可引导语言模型行为并提升其零样本推理能力。然而，这种提升在不同任务或实例间表现不一，表明零样本与角色扮演提示可能具有互补优势而非单一更优。基于此洞察，本文提出Persona Switch——一种动态结合两种提示策略的解码方法。该方法逐步进行，在每一步通过比较输出置信度（以logit gap衡量）来选择表现更优的生成结果。在多个主流大模型上的实验表明，Persona Switch持续优于现有基线，准确率最高提升5.13%。此外，研究进一步验证了输出置信度作为可靠输出选择指标的有效性。
原文摘要 · Abstract (English)
Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improvements are inconsistent across different tasks or instances. This inconsistency suggests that zero-shot and role-play prompting may offer complementary strengths rather than one being universally superior. Building on this insight, we propose Persona Switch, a novel decoding method that dynamically combines the benefits of both prompting strategies. Our method proceeds step-by-step, selecting the better output between zero-shot and role-play prompting at each step by comparing their output confidence, as measured by the logit gap. Experiments with widely-used LLMs demonstrate that Persona Switch consistently outperforms competitive baselines, achieving up to 5.13% accuracy improvement. Furthermore, we show that output confidence serves as an informative measure for selecting the more reliable output.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。