发表机构
New York University; New York University Abu Dhabi; McGill University; MBZUAI（纽约大学; 纽约大学阿布扎比分校; 麦吉尔大学; 穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ANIMASK通过冻结故事世界并对比有无角色人格的模型行为，揭示模型默认倾向在角色扮演中的贡献，发现模型默认行为常已符合人格，且在分歧时更谨慎。
AI 中文摘要
当语言模型扮演一个角色时，观察到的行为既反映了被分配的人格，也反映了演员模型本身的默认倾向。现有评估要么单独测试人格保真度，要么单独测试模型默认行为，但都没有说明，在某个有后果的具体选择中，人格改变了什么，而模型的默认行为又保留了什么。我们引入了ANIMASK，一个模拟框架，它将书籍和剧本冻结成故事世界，其中的角色根据自己的动机行动，并从冻结点重放每个故事。我们将作者的续写作为人类参考，通过故事内访谈验证每个人格始终存在，并在每个决策点将角色的行动与移除人格后模型产生的行动进行比较。在40个故事、6个演员模型和3,846个决策点上，重放结果以共同的方向偏离其正典，趋向于更平淡、更冷静的故事，留下未解决的张力。人格在整个过程中保持存在并被遵守。在四分之三的选择中，模型的默认行为已经落在人格可接受的范围内，而在两者分歧之处，模型是谨慎的一方，在人格会推进的地方保持不动。人格保证了角色是谁，而模型设定了角色会走多远。
英文摘要
When a language model plays a character, the observed behavior reflects both the assigned persona and the default dispositions of the actor model itself. Existing evaluations test persona fidelity or model defaults in isolation, but neither says, at a specific choice with consequences, what the persona changed and what the model's default kept. We introduce ANIMASK, a simulation framework that freezes books and scripts into story worlds whose characters act on their own motivations and replays each story from its freeze point. We hold out the author's continuation as a human reference, verify through in-story interviews that each persona remains present, and at every decision point compare the character's action with what the model produces when the persona is removed. Across 40 stories, 6 actor models, and 3,846 decision points, the replays converge away from their canons in one shared direction, toward flatter, cooler stories that leave their tensions open. The personas stay present and obeyed throughout. On three choices in four the model's default already falls inside what the persona accepts, and where the two diverge the model is the cautious one, holding where the persona would press. The persona guarantees who the character is, and the model sets how far the character will go.
Comments38 pages, 6 figures, 14 tables
