使用 LLM 打造可定制角色：一个角色驱动的角色扮演智能体框架
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework
AI总结：
本文提出基于LLM的可定制对话智能体框架及SimsConv数据集，通过个性化特征注入模拟真实角色，并构建SimsChat智能体，在角色一致性与知识准确性上优于现有模型。
摘要：
大型语言模型（LLMs）展现出理解指令和生成类人文本的卓越能力，使得超越基本行为复制的复杂智能体模拟成为可能。然而，创建自由可定制角色的潜力仍未被充分探索。我们引入了可定制对话智能体框架（Customisable Conversation Agent Framework），该框架利用 LLMs 通过个性化特征注入来模拟真实世界角色，从而根据用户偏好实现多样化角色创建。我们提出了 SimsConv 数据集，包含 68 个定制角色和跨越 1,360 个真实世界场景的 13,971 轮多轮角色扮演对话。角色最初使用预定义元素（职业、抱负、特质、技能）进行定制，随后通过个人和社交档案进行扩展。在此基础上，我们推出了 SimsChat，这是一个自由可定制的角色扮演智能体，融合了各种现实设定和特定主题的角色互动。在 SimsConv 和 WikiRoleEval 数据集上的实验结果表明，与现有模型相比，SimsChat 在保持角色一致性、知识准确性以及恰当的问题拒绝方面表现出卓越的性能。我们的框架为开发更准确、更可定制的人类拟像提供了有价值的见解。我们的数据和代码已在 https://github.com/Bernard-Yang/SimsChat 公开。
英文摘要：
Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication. However, the potential for creating freely customisable characters remains underexplored. We introduce the Customisable Conversation Agent Framework, which employs LLMs to simulate real-world characters through personalised characteristic feature injection, enabling diverse character creation according to user preferences. We propose the SimsConv dataset, comprising 68 customised characters and 13,971 multi-turn role-playing dialogues across 1,360 real-world scenes. Characters are initially customised using pre-defined elements (career, aspiration, traits, skills), then expanded through personal and social profiles. Building on this, we present SimsChat, a freely customisable role-playing agent incorporating various realistic settings and topic-specified character interactions. Experimental results on both SimsConv and WikiRoleEval datasets demonstrate SimsChat's superior performance in maintaining character consistency, knowledge accuracy, and appropriate question rejection compared to existing models. Our framework provides valuable insights for developing more accurate and customisable human simulacra. Our data and code are publicly available at https://github.com/Bernard-Yang/SimsChat.
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。
