@article{cheng-etal-2026-psymem,
    title = "{P}sy{M}em: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing {LLM}s",
    author = "Cheng, Xilong  and
      Qin, Yunxiao  and
      Tan, Yuting  and
      Li, Zhengnan  and
      Wang, Ye  and
      Xiao, Hongjiang  and
      Zhang, Yuan",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-latest-mitpress-cl-tacl/2026.tacl-1.24/",
    doi = "10.1162/tacl.a.645",
    pages = "510--529",
    abstract = "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."
}