DiPS：高风险说服代理的对话策略选择
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
AI总结：
针对高风险场景中说服策略需个性化的问题，提出DiPS框架，基于Q-learning动态选择说服策略，在火灾疏散模拟和真实人机交互中提升成功率。
摘要：
大型语言模型（LLM）在高风险场景中的说服能力往往不足。人们的个性特征和关注点需要量身定制的策略，而非一刀切的方法。为应对这一挑战，我们聚焦于消防救援场景（操作员需说服居民撤离）作为高风险说服领域，提出对话策略选择（DiPS）框架，这是一种Q-learning框架，用于根据不断变化的对话上下文动态选择说服策略。具体而言，我们训练一个评判器，以最大化撤离成功概率为目标，在每一轮根据居民最近的对话历史选择说服策略。随后，我们在模拟和真实人机交互中评估DiPS与多个基线方法的性能。结果发现，DiPS相比零样本LLM和通用RAG增强方法实现了更高的撤离成功率。
英文摘要：
Large Language Models (LLMs) often struggle with persuasion in high-stakes scenarios. People's individual personalities and concerns require tailored strategies rather than a one-size-fits-all approach. To address this challenge, we focus on a fire-rescue scenario in which an operator must persuade a resident to evacuate as a high-stakes persuasion domain and propose Dialogue Policy Selection (DiPS), a Q-learning framework to dynamically select persuasion strategies adapted to the evolving conversational context. Specifically, we train a critic, trained to maximize the chance of evacuation success, to select a persuasion policy at each turn based on the resident's recent utterances. We then evaluate DiPS against multiple baselines in both simulated and real human interactions. We find that DiPS achieves higher evacuation success than a zero-shot LLM and generic RAG-augmented approach.
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。
