别射流风：使用非线性朴素贝叶斯与注意机制的主题连续性模型
Don't Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention
AI总结：
本文提出了一种基于非线性朴素贝叶斯与注意力机制的主题连续性模型，用于评估对话响应与初始话题的一致性，有效处理长对话并提升可解释性。
摘要：
利用大型语言模型（LLM）作为聊天机器人在多样化的商业场景中常常面临维持话题连续性的挑战。话题的突然转变可能导致用户体验差和计算资源的低效利用。在本文中，我们提出了一种主题连续性模型，旨在评估响应是否与初始对话主题一致。我们的模型基于将相应的自然语言理解（NLU）模型扩展为可量化术语的朴素贝叶斯方法。随后，我们引入了注意力机制和对数非线性性，以增强其捕捉话题连续性的能力。这种方法使我们能够将NLU模型转换为可解释的分析公式。与许多受token限制的NLU模型不同，我们提出的模型可以无缝处理任意长度的对话，具有线性时间复杂度。此外，注意力机制显著提高了模型在复杂对话中识别话题连续性的能力。根据我们的实验，我们的模型在处理长而复杂的对话方面始终优于传统方法。这种独特能力为我们提供了一个机会，确保LLM的负责任和可解释的使用。
英文摘要：
Utilizing Large Language Models (LLM) as chatbots in diverse business scenarios often presents the challenge of maintaining topic continuity. Abrupt shifts in topics can lead to poor user experiences and inefficient utilization of computational resources. In this paper, we present a topic continuity model aimed at assessing whether a response aligns with the initial conversation topic. Our model is built upon the expansion of the corresponding natural language understanding (NLU) model into quantifiable terms using a Naive Bayes approach. Subsequently, we have introduced an attention mechanism and logarithmic nonlinearity to enhance its capability to capture topic continuity. This approach allows us to convert the NLU model into an interpretable analytical formula. In contrast to many NLU models constrained by token limits, our proposed model can seamlessly handle conversations of any length with linear time complexity. Furthermore, the attention mechanism significantly improves the model's ability to identify topic continuity in complex conversations. According to our experiments, our model consistently outperforms traditional methods, particularly in handling lengthy and intricate conversations. This unique capability offers us an opportunity to ensure the responsible and interpretable use of LLMs.
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。
