@inproceedings{ji-etal-2025-enhancing,
    title = "Enhancing Persona Consistency for {LLM}s' Role-Playing using Persona-Aware Contrastive Learning",
    author = "Ji, Ke  and
      Lian, Yixin  and
      Li, Linxu  and
      Gao, Jingsheng  and
      Li, Weiyuan  and
      Dai, Bin",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1344/",
    pages = "26221--26238",
    ISBN = "979-8-89176-256-5",
    abstract = "In recent years, large language models (LLMs) have achieved breakthrough progress in many dialogue generation tasks. However, their lack of emotion and fine-grained role awareness limits the model{'}s ability to provide personalized and diverse interactions further. Current methods face high costs in collecting high-quality annotated data for scenarios such as role-playing, and traditional human alignment methods are difficult to deploy due to the inherent diversity of model behavior in role-playing scenarios. Inspired by the alignment of models for safety behaviors through RLHF (Reinforcement Learning from Human Feedback), in this paper, we revisit model role-playing behavior from the perspective of persona alignment and propose a novel annotation-free framework named Persona-Aware Contrastive Learning (PCL) to align LLMs' behavior during role-playing, enhancing the model{'}s role consistency. Specifically, we first design a role chain method to encourage the model to self-question based on the role characteristics and dialogue context to adjust personality consistency. Then, we further enhance the model{'}s role-playing strategy through iterative adversarial modeling between the use of role characteristics and not. Experiments on both black-box and white-box LLMs show that LLMs equipped with PCL significantly outperform vanilla LLMs under automatic evaluation methods (CharEval {\&} GPT-4) and human expert evaluation."
}