DIPLOMAT：面向礼貌且有说服力的职场谈判对话的对话跨度感知直接偏好优化
DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues
- Indian Institute of Technology Patna（印度理工学院巴特那分校）
- University of Caen Normandy（卡昂诺曼底大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对职场谈判中礼貌与说服力不足的问题，提出DIPLOMAT对话系统，采用对话跨度感知直接偏好优化（DSA-DPO）训练，并构建PROWESS数据集，实验证明其生成响应在连贯性、礼貌性和说服力上优于基线。
AI中文摘要：
有效的职场谈判需要平衡多个目标，包括实现任务目标、维护职业关系以及建设性地解决冲突。然而，误解、偏好不一致和人际摩擦常常阻碍成功的结果。礼貌通过培养信任、减少紧张和防止事态升级来缓解这些挑战，而有说服力的沟通有助于克服阻力、协调偏好并引导参与者达成互利协议。受这些见解的启发，我们提出了DIPLOMAT，一个用于礼貌且有说服力的职场谈判的对话系统。为支持其开发，我们引入了PROWESS，一个通过多智能体框架生成的多轮职场谈判对话数据集，并丰富了谈判策略、礼貌水平和说服策略。DIPLOMAT使用对话跨度感知直接偏好优化（DSA-DPO）进行训练，这是一种新颖的偏好学习目标，可识别用于偏好对齐的关键对话跨度。这使得DIPLOMAT能够生成上下文连贯的响应，在交互中采用预期的谈判策略、保持礼貌并融入有效的说服策略。在PROWESS上的自动和人工评估证实，DIPLOMAT在生成连贯、礼貌且有说服力的谈判响应方面始终优于基线。
英文摘要：
Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present DIPLOMAT, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce PROWESS, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched withnegotiation strategies, politeness levels, persuasive strategies. DIPLOMAT is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables DIPLOMAT to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.
