以最低训练成本实现实时对话
Enabling Real-Time Conversations with Minimal Training Costs
AI总结：
针对传统大语言模型对话系统无法实时交互且现有双工方案训练成本高的问题，提出一种仅需少量额外训练的双工解码方法，通过对话查询与响应的并行解码实现信道分用，以低成本提升人机交互自然度。
摘要：
大语言模型（LLM）已展现出通过对话交互提升人类效率的能力。传统基于大语言模型的对话系统采用轮次式范式运行，无法在响应生成过程中实现实时交互。为解决这一局限，研究人员提出了双工模型（duplex models），这类模型可动态适应用户输入，助力实现实时交互反馈，但这类方法通常需要大量计算资源才能获得该能力。为降低开销，本文提出一种全新的双工解码方法，仅需极少额外训练即可为大语言模型赋予双工能力。具体而言，该方法对对话中的查询和响应采用并行解码，有效实现了一种信道分用解码策略。实验结果表明，本文提出的方法以极低的训练成本，显著提升了用户与AI交互的自然度与拟人度。
英文摘要：
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.
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。
