Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignment-induced biases in existing methods: a positive moral bias, where characters uniformly adopt agreeable stances (e.g. always saying lying is bad), and a helpful assistant bias, where characters invariably answer questions directly (e.g. never refusing or deflecting). While such tendencies suit instruction-following systems, they suppress dramatic tension and yield predictable characters, stemming from maximum likelihood training and assistant fine-tuning. To address this, we introduce PersonaWeaver, a framework that disentangles world-building (roles, demographics) from behavioral-building (moral stances, interactional styles), yielding characters with more diverse reactions and moral stances, as well as second-order diversity in stylistic markers like length, tone, and punctuation. Code: https://github.com/mqraitem/Persona-Weaver

翻译：程序化内容生成通过关卡、地图与任务构建了广阔的虚拟世界，但大规模角色生成仍是一个未充分探索的领域。我们发现了现有方法中两类由对齐诱导的偏差：正向道德偏差——角色普遍采取迎合性立场（例如始终认为说谎是错的），以及助益性助手偏差——角色总是直接回答问题（例如从不拒绝或回避）。虽然这些倾向适用于指令遵循系统，但它们抑制了戏剧张力，导致角色可预测。这源于最大似然训练与助手的微调。为解决此问题，我们提出PersonaWeaver框架，该框架将世界构建（角色、人口统计特征）与行为构建（道德立场、互动风格）解耦，从而生成具有更多元反应与道德立场的角色，并在风格标记（如长度、语气与标点符号）中实现二阶多样性。代码：https://github.com/mqraitem/Persona-Weaver