通过心理属性与显式记忆控制提升角色扮演大模型的可信度
PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
- 引入26个心理指标精细刻画角色性格
- 训练模型显式对齐回复与记忆，实现动态记忆响应
- 在5414个角色数据上训练，显著提升角色一致性
现有基于大语言模型的角色扮演方法多依赖表面文本描述或简单指标，难以全面建模角色的内在与外在特征。同时，通常用隐式模型知识或基础检索增强生成来模拟记忆，缺乏显式记忆对齐，导致记忆不一致。这两方面削弱了角色扮演模型在可信社交模拟等场景中的可靠性。为此，我们提出PsyMem框架，融合细粒度心理属性与显式记忆控制。PsyMem通过26个心理指标补充角色描述，实现更精准的性格建模；并引入记忆对齐训练，显式引导模型在推理时依据记忆生成回应，支持动态记忆控制。在自建数据集（含5,414个角色和38,962条对话，均来自小说）上训练Qwen2.5-7B-Instruct，得到的PsyMem-Qwen模型在角色扮演任务中表现最优，人类评估显示其在自然度和角色忠实度上均领先于基线模型。
原文摘要 · Abstract (English)
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.
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。