用动态事件提升动漫角色对话的自然感和互动性
HonkaiChat: Companions from Anime that feel alive!
- 在对话提示中嵌入动态事件，让角色回应更灵活
- 对比基线模型，对话自然度提升且幻觉减少
- 适合想打造沉浸式角色扮演体验的开发者
现代对话代理，包括动漫主题聊天机器人，通常反应被动且以性格驱动为主，难以体现人类互动的动态特性。本文提出一种事件驱动的对话框架，通过在对话提示中嵌入动态事件，并在角色特定数据上微调模型来解决这一问题。在GPT-4上的评估及与行业领先基线的对比表明，事件驱动提示显著提升了对话参与度和自然度，同时减少了幻觉。论文以《崩坏：星穹铁道》为场景，展示了该方法在创建拟真聊天机器人交互中的潜力，验证了基于动态事件系统的角色扮演对话具有变革前景。
原文摘要 · Abstract (English)
Modern conversational agents, including anime-themed chatbots, are frequently reactive and personality-driven but fail to capture the dynamic nature of human interactions. We propose an event-driven dialogue framework to address these limitations by embedding dynamic events in conversation prompts and fine-tuning models on character-specific data. Evaluations on GPT-4 and comparisons with industry-leading baselines demonstrate that event-driven prompts significantly improve conversational engagement and naturalness while reducing hallucinations. This paper explores the application of this approach in creating lifelike chatbot interactions within the context of Honkai: Star Rail, showcasing the potential for dynamic event-based systems to transform role-playing and interactive dialogue.
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。