发表机构
University of North Carolina at Chapel Hill; North Carolina State University（北卡罗来纳大学教堂山分校; 北卡罗来纳州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探索大语言模型行为中叙事框架的影响，通过构建游戏识别叙事先验，发现其解释行为方差能力强且与任务成功相关，还明确跨叙事角色效应源于行为锚点，框架可推广并产生改进跨叙事转移的角色选择方法。
AI 中文摘要
角色提示被广泛用于引导大语言模型智能体的行为，然而任务的叙事框架可能比指定的角色更重要。我们通过结构同构分离出这种效应，构建了三个基于文本的调查游戏，它们具有相同的行动空间、阶段进展和资源限制，仅任务叙事不同：疾病调查、信息技术故障排除和谋杀之谜。在涉及3个模型和10个角色的1890次会话中，我们识别出叙事先验：由任务的故事框架激活的系统行动倾向，与其决策结构无关。叙事先验解释的行为方差比角色多5到31倍，在不同模型架构中一致，并且在三个领域中的两个与任务成功呈负相关。跨叙事转移的角色效应源于行为锚点，即语言直接映射到共享行动的角色描述。因果干预证实了这一点：从高转移角色中删除锚点词会使跨叙事一致性降低95%。我们的框架还推广到一个保留的第四个叙事，并产生了一种角色选择方法，可改善跨叙事转移。这些结果表明，在叙事变化中幸存的大语言模型行为应基于具体行动而非抽象描述。
英文摘要
Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than the assigned persona. We isolate this effect through structural isomorphism, constructing three text-based investigation games that share the same action space, stage progression, and resource constraints while varying only task narrative: disease investigation, IT troubleshooting, and murder mystery. Across 1,890 sessions spanning 3 models and 10 personas, we identify narrative priors: systematic action tendencies activated by a task's story framing, independent of its decision structure. Narrative priors explain 5-31x more behavioral variance than persona, are consistent across model architectures, and in two of three domains are negatively associated with task success. Persona effects that do transfer across narratives arise from behavioral anchors, persona descriptions whose language maps directly onto shared actions. Causal interventions confirm this: removing anchor words from a high-transfer persona reduces cross-narrative consistency by 95%. Our framework also generalizes to a held-out fourth narrative and yields a persona-selection method that improves cross-narrative transfer. These results suggest that LLM behavior that survives narrative changes should be grounded in concrete actions rather than abstract descriptions.
CommentsAccepted at COLM 2026. 10 pages, 3 figures, 16 tables in appendix
