PsyMem：面向高级角色扮演大语言模型的细粒度心理对齐与显式记忆控制
PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
AI总结：
针对角色扮演LLM在角色心理建模与记忆一致性上的不足，提出PsyMem框架，引入26项心理指标和显式记忆对齐训练，提升拟人度与角色保真度。
摘要：
现有的基于大语言模型（LLM）的角色扮演方法通常依赖表层文本描述或过于简单的指标，无法充分建模角色的内在与外在维度。此外，它们通常借助隐式模型知识或基础检索增强生成来模拟角色记忆，缺乏显式记忆对齐，从而损害记忆一致性。这两个问题削弱了角色扮演LLM在可信社会模拟等多种应用中的可靠性。为解决上述局限，我们提出PsyMem，这是一个融合细粒度心理属性与显式记忆控制的新型角色扮演框架。PsyMem以26项心理指标补充文本描述，以细致建模角色。同时，PsyMem实施记忆对齐训练，显式训练模型使角色回应与记忆保持一致，从而在推理阶段实现动态的记忆受控回应。通过在专门设计的数据集上训练Qwen2.5-7B-Instruct（包含从小说中提取的5,414个角色和38,962段对话），所得模型PsyMem-Qwen在角色扮演任务上优于基线模型，并在拟人度和角色保真度方面取得最佳性能。
英文摘要：
Existing LLM-based role-playing methods often rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions. Additionally, they typically simulate character memory with implicit model knowledge or basic retrieval augment generation without explicit memory alignment, compromising memory consistency. The two issues weaken reliability of role-playing LLMs in several applications, such as trustworthy social simulation. To address these limitations, we propose PsyMem, a novel framework integrating fine-grained psychological attributes and explicit memory control for role-playing. PsyMem supplements textual descriptions with 26 psychological indicators to detailed model character. Additionally, PsyMem implements memory alignment training, explicitly trains the model to align character's response with memory, thereby enabling dynamic memory-controlled responding during inference. By training Qwen2.5-7B-Instruct on our specially designed dataset (including 5,414 characters and 38,962 dialogues extracted from novels), the resulting model, termed as PsyMem-Qwen, outperforms baseline models in role-playing, achieving the best performance in human-likeness and character fidelity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
