发表机构
Indian Institute of Technology Patna; Ramakrishna Mission Vivekananda Educational and Research Institute; Accenture Labs（印度巴特那印度理工学院; 罗摩克里希纳使命维韦卡南达教育与研究学院; 埃森哲实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对保险领域说服性对话需求，提出PersuaRL强化学习框架，结合自主构建的InsureDial数据集，在基准数据集上验证其优于基线，可生成高说服性的对话响应。
AI 中文摘要
大型语言模型（LLM）正通过为客服、数字销售、保险等领域部署对话智能体，彻底变革数字通信。这些基于LLM构建的智能体可理解用户输入、检索相关信息并生成连贯响应，不过它们虽擅长事实性交流，却常缺乏开展真正说服性、上下文敏感对话的能力，尤其在信任与清晰度至关重要的保险领域。针对保险领域的这一需求，本研究聚焦于提升基于LLM的数字智能体的说服能力。为支撑该研究，我们推出InsureDial——一个捕捉机动车保险交互中说服性交流细微差别的说服性保险对话数据集。我们提出PersuaRL，这一基于强化学习的框架可让LLM驱动的对话智能体，在不断变化的对话上下文引导下，自适应探索、选择并协调多个专家模块的策略，以实现更有效的说服。我们在包括InsureDial在内的两个基准说服性对话数据集上开展了大量自动、人工及定性评估，评估结果始终表明，PersuaRL的表现优于基线方法，能生成上下文恰当且极具说服性的响应。
英文摘要
Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer service, digital sales, and insurance. These agents, built on LLMs, can understand user input, retrieve relevant information, and generate coherent responses. However, while they excel at factual communication, they often lack the ability to engage in truly persuasive, context-sensitive dialogue, especially in domains like insurance, where trust and clarity are critical. Building on this need within the insurance domain, our work focuses on improving the persuasiveness of digital agents, aka LLMs. To support this, we introduce InsureDial, a Persuasive Insurance Dialogue dataset, designed to capture the nuances of persuasive communication specific to motor insurance interactions. We introduce PersuaRL, a reinforcement learning-based framework that equips LLM-driven dialogue agents with the ability to adaptively explore, select, and coordinate strategies across multiple expert modules, guided by the evolving dialogue context, to achieve more effective persuasion. We conduct extensive automatic human and qualitative evaluations on two benchmark persuasion dialogue datasets, including our InsureDial. Our evaluations consistently demonstrate that PersuaRL outperforms baseline, generating contextually appropriate and highly persuasive responses.
CommentsEMNLP Findings 2026
