让大模型对话实时响应，训练成本极低。
Enabling Real-Time Conversations with Minimal Training Costs
- 并行解码用户输入与模型回复，实现双向交互
- 仅需少量训练即可显著提升对话自然度
- 适合追求低开销实时对话系统的开发者
大型语言模型（LLMs）通过对话交互已展现出提升人类效率的能力。传统基于轮次的对话系统在生成回复时无法实现实时互动。为解决此问题，研究者提出双工模型，可动态适应用户输入，支持实时反馈。但此类方法通常需要大量计算资源。本文提出一种新的双工解码方法，使LLM具备双工能力，且只需极小额外训练成本。具体而言，该方法在对话中并行解码查询与响应，实现信道分复用式解码策略。实验结果表明，该方法显著提升了用户-智能体交互的自然度和类人程度，同时训练成本极低。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating on a turn-based paradigm, preclude real-time interaction during response generation. To address this limitation, researchers have proposed duplex models. These models can dynamically adapt to user input, facilitating real-time interactive feedback. However, these methods typically require substantial computational resources to acquire the ability. To reduce overhead, this paper presents a new duplex decoding approach that enhances LLMs with duplex ability, requiring minimal additional training. Specifically, our method employs parallel decoding of queries and responses in conversations, effectively implementing a channel-division-multiplexing decoding strategy. Experimental results indicate that our proposed method significantly enhances the naturalness and human-likeness of user-AI interactions with minimal training costs.
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。