利用思维链推理将销售人员的对话策略注入大语言模型
Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning
AI总结：
本文提出改进数据集SalesBot 2.0及基于思维链推理的新模型SalesAgent，通过策略性提示注入大语言模型常识与销售人员对话策略，有效提升了话题转换、意图理解与策略选择能力，增强了销售对话的连贯性与自然度。
摘要：
对话系统和语料库的近期研究主要关注两大类别：面向任务的对话（TOD）和开放域对话（闲聊）。TOD系统帮助用户完成特定任务，而开放域系统旨在创造引人入胜的对话。然而，在真实场景中，用户意图往往在交互过程中才逐渐显露。近期的一项研究引入了SalesBot，它模拟从闲聊过渡到面向任务场景的对话，以训练销售智能体。遗憾的是，初始数据缺乏平滑的过渡和连贯的长对话，导致销售与客户交互的自然度较差。为了解决这些问题，本文提出了改进的数据集SalesBot 2.0。它通过策略性提示利用大语言模型（LLMs）的常识知识。此外，我们引入了一个名为SalesAgent的新模型，该模型基于销售人员的交互进行训练，并使用思维链（CoT）推理。该模型在话题转换、理解用户意图和选择适当策略方面表现出色。使用多样化用户模拟的实验验证了本方法在控制LLMs对话策略方面的有效性。此外，SalesBot 2.0增强了连贯性并降低了攻击性，从而促进了模型在销售与客户交互方面更好的学习。
英文摘要：
Recent research in dialogue systems and corpora has focused on two main categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems help users accomplish specific tasks, while open-domain systems aim to create engaging conversations. However, in real-world scenarios, user intents are often revealed during interactions. A recent study introduced SalesBot, which simulates dialogues transitioning from chit-chat to task-oriented scenarios to train sales agents. Unfortunately, the initial data lacked smooth transitions and coherent long-turn dialogues, resulting in poor naturalness in sales-customer interactions. To address these issues, this paper presents SalesBot 2.0, an improved dataset. It leverages commonsense knowledge from large language models (LLMs) through strategic prompting. Additionally, we introduce a novel model called SalesAgent, trained on salesperson's interactions, using chain-of-thought (CoT) reasoning. This model excels in transitioning topics, understanding user intents, and selecting appropriate strategies. Experiments using diverse user simulations validate the effectiveness of our method in controlling dialogue strategies in LLMs. Furthermore, SalesBot 2.0 enhances coherence and reduces aggression, facilitating better model learning for sales-customer interactions.
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。
