用人格提示提升大模型战略决策能力，需通过中介机制转化才有效。
Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?
- 设计中介模块将人格描述转化为可操作的策略值
- 特定战略型人格配合中介使游戏胜率提升18.7%
- 方法融合心理测量学原理，适合研究人格对决策影响
尽管人格提示能引发大语言模型生成不同风格的文本，但其是否带来可测量的行为差异仍不明确，尤其在我们开源的对抗性战略环境（PERIL）中。本文研究人格提示对战略表现的影响，比较基于人格的启发式策略与人工设定策略的效果。结果表明，与战略思维相关的特定人格可提升游戏表现，但仅当使用中介模块将人格转化为启发式数值时才有效。该中介模块受探索性因子分析启发，将模型生成的库存响应映射为启发式规则。相比直接推断的启发式，新方法显著提升了可靠性和表面效度，使我们能更准确地研究人格类型对决策的影响。该研究深化了对人格提示如何影响大模型决策的理解，并提出一种应用心理测量学原则生成启发式的有效方法。
原文摘要 · Abstract (English)
Although persona prompting in large language models appears to trigger different styles of generated text, it is unclear whether these translate into measurable behavioral differences, much less whether they affect decision-making in an adversarial strategic environment that we provide as open-source. We investigate the impact of persona prompting on strategic performance in PERIL, a world-domination board game. Specifically, we compare the effectiveness of persona-derived heuristic strategies to those chosen manually. Our findings reveal that certain personas associated with strategic thinking improve game performance, but only when a mediator is used to translate personas into heuristic values. We introduce this mediator as a structured translation process, inspired by exploratory factor analysis, that maps LLM-generated inventory responses into heuristics. Results indicate our method enhances heuristic reliability and face validity compared to directly inferred heuristics, allowing us to better study the effect of persona types on decision making. These insights advance our understanding of how persona prompting influences LLM-based decision-making and propose a heuristic generation method that applies psychometric principles to LLMs.
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。