让AI聊天像真人一样思考、等待、按节奏发言
Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chat
- 每步决策是否发送或等待，模拟人类真实对话节奏
- 在自然度和互动性上超越前代模型，人类评测通过率更高
- 适合需要真实社交体验的对话系统研发者参考
即时消息中的社交对话通常由一系列短消息构成。现有分步生成式AI聊天系统虽将单次生成拆分为多条消息顺序发送，但缺乏主动等待机制，消息节奏生硬。为此，我们提出Stephanie2，一种新一代分步决策对话代理。该模型引入主动等待机制与消息节奏自适应能力，显式决定每一步是否发送或等待，并将延迟建模为思考时间与打字时间之和，实现更自然的对话节奏。我们还设计了一种基于时间窗口的双代理对话系统，生成伪对话历史用于人类与自动评估。实验表明，Stephanie2在自然度与互动性等指标上显著优于Stephanie1，且在角色识别图灵测试中通过率更高。
原文摘要 · Abstract (English)
Instant-messaging human social chat typically progresses through a sequence of short messages. Existing step-by-step AI chatting systems typically split a one-shot generation into multiple messages and send them sequentially, but they lack an active waiting mechanism and exhibit unnatural message pacing. In order to address these issues, we propose Stephanie2, a novel next-generation step-wise decision-making dialogue agent. With active waiting and message-pace adaptation, Stephanie2 explicitly decides at each step whether to send or wait, and models latency as the sum of thinking time and typing time to achieve more natural pacing. We further introduce a time-window-based dual-agent dialogue system to generate pseudo dialogue histories for human and automatic evaluations. Experiments show that Stephanie2 clearly outperforms Stephanie1 on metrics such as naturalness and engagement, and achieves a higher pass rate on human evaluation with the role identification Turing test.
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。