为角色扮演设计轻量模型，剪枝不丢表现
Persona-Pruner: Sculpting Lightweight Models for Role-Playing
- 从单个角色描述中提取专属子网络，实现精准剪枝
- 在RoleBench上性能损失比最强基线低93.8%
- 适合需要大量角色并行的对话系统场景
语言模型在角色扮演聊天机器人中表现出色，能提供一致且风格化的交互。但在真实应用（如多个非玩家角色同时互动的生态系统）中，全规模通用模型带来巨大计算开销。本文质疑为单一角色配置完整模型的必要性，提出角色身份仅需模型部分能力。发现简单剪枝会严重损害特定角色表现，因无法区分冗余知识与核心角色特征。为此提出Persona-Pruner框架，通过角色描述提取专属子网络，构建轻量角色模型。实验显示，该方法显著优于现有主流剪枝技术，在RoleBench的LLM-as-a-judge评分上，性能下降相比最强基线减少93.8%，同时保留通用语言模型能力。代码已开源。
原文摘要 · Abstract (English)
Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at https://github.com/jsu-kim/Persona-Pruner.
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。