让AI角色更真实：打破千篇一律的对话模式
Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation
- 分离角色设定与行为模式，实现多样人格生成
- 生成角色在道德立场和互动风格上差异明显
- 适合游戏剧情、虚拟角色等需要个性化的场景
程序化内容生成已广泛应用于虚拟世界的关卡、地图和任务设计，但大规模角色生成仍处于探索阶段。现有方法存在两种对齐偏差：一是正向道德偏差，角色统一持赞同态度（如始终认为说谎是错误的）；二是助手机器偏差，角色总是直接回答问题（如从不拒绝或回避）。这些倾向虽适合指令遵循系统，却削弱了戏剧张力，导致角色过于可预测，根源在于最大似然训练和助手微调。为此，我们提出PersonaWeaver框架，将世界观构建（角色身份、人口统计）与行为构建（道德立场、交互风格）解耦，生成具有更丰富反应和道德立场的角色，同时在表达风格如长度、语气和标点上呈现二级多样性。代码已开源。
原文摘要 · Abstract (English)
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
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。