PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues

2026-04-20

AI Summary

Existing negotiation dialogue systems struggle to respond strategically to emotions and lack interpretability, hindering trust formation and interaction effectiveness. This work proposes an Emotion-aware Negotiation Strategy Chain-of-Thought (ENS-CoT) reasoning mechanism, integrated with a self-training approach based on Direct Preference Optimization (DPO), to unify emotional intelligence and explainability in negotiation for the first time. To support this framework, the authors introduce two new datasets—JobNego and ResNego—capturing job interview and resource allocation scenarios, respectively. Experimental results demonstrate that the proposed method significantly improves emotional appropriateness, explainability, and overall negotiation performance over baseline approaches, as evidenced by both automatic metrics and human evaluations.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Humans and AI: Emotional Intelligence
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Emotion plays a pivotal role in shaping negotiation outcomes, influencing trust, cooperation, and long-term relationships. Developing negotiation dialog systems that can recognize and respond strategically to emotions is, therefore, essential to create more effective human-centered interactions. Beyond generating emotionally appropriate responses, interpretability - understanding how a system generates a particular emotion-aware response, is critical for fostering reliability and building rapport. Driven by these aspects, in this work, we introduce PRISMA, an interpretable emotionally intelligent negotiation dialogue system targeting two application domains, viz. job interviews and resource allocation. To enable interpretability, we propose an Emotion-aware Negotiation Strategy-informed Chain-of-Thought (ENS-CoT) reasoning mechanism, which mimics human negotiation by perceiving, understanding, using, and managing emotions. Leveraging ENS-CoT, we curate two new datasets: JobNego (for job interview negotiation) and ResNego (for resource allocation negotiation). We then leverage these datasets to develop PRISMA by augmenting self-training with Direct Preference Optimization (DPO), guiding agents toward more accurate, interpretable, and emotionally appropriate negotiation responses. Automatic and human evaluation on JobNego and ResNego datasets demonstrate that PRISMA substantially enhances interpretability and generates appropriate emotion-aware responses, while improving overall negotiation effectiveness.

Problem

• emotionally intelligent negotiation
• interpretable dialogue system
• emotion-aware response
• negotiation dialogue
• human-centered interaction

Innovation

• Emotion-aware Negotiation
• Chain-of-Thought Reasoning
• Direct Preference Optimization
• Interpretable AI
• Self-Training