EQ-Negotiator: An Emotion-Reasoning LLM Agent in Credit Dialogues

2025-03-27

AI Summary

Existing LLM-based credit dialogue agents exhibit rigid emotional expression, relying solely on passive empathy and lacking proactive regulation of customers’ sustained negative affect. This work proposes an emotion-aware and reasoning-enhanced LLM negotiation agent. First, fine-grained emotion recognition is performed using a pre-trained language model (PLM). Second, game-theoretic modeling captures strategic emotional interactions between interlocutors, while a hidden Markov model (HMM) enables dynamic emotional state inference and response intonation optimization. To our knowledge, this is the first framework to jointly embed game theory and HMM into an LLM’s emotional decision-making architecture, shifting the paradigm from passive empathy to active emotional guidance. Evaluated on real-world credit dialogue data, the method significantly improves emotion response accuracy (+18.3%) and customer satisfaction (+22.7%), effectively mitigates adversarial behaviors, and increases negotiation success rate by 15.4%.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Affective Computing

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
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

While large language model (LLM)-based chatbots have been applied for effective engagement in credit dialogues, their capacity for dynamic emotional expression remains limited. Current agents primarily rely on passive empathy rather than affective reasoning. For instance, when faced with persistent client negativity, the agent should employ strategic emotional adaptation by expressing measured anger to discourage counterproductive behavior and guide the conversation toward resolution. This context-aware emotional modulation is essential for imitating the nuanced decision-making of human negotiators. This paper introduces an EQ-negotiator that combines emotion sensing from pre-trained language models (PLMs) with emotional reasoning based on Game Theory and Hidden Markov Models. It takes into account both the current and historical emotions of the client to better manage and address negative emotions during interactions. By fine-tuning pre-trained language models (PLMs) on public emotion datasets and validating them on the credit dialogue datasets, our approach enables LLM-based agents to effectively capture shifts in client emotions and dynamically adjust their response tone based on our emotion decision policies in real-world financial negotiations. This EQ-negotiator can also help credit agencies foster positive client relationships, enhancing satisfaction in credit services.

Problem

• Enhancing emotional expression in LLM-based credit dialogue agents
• Integrating emotion sensing with Game Theory for dynamic adaptation
• Improving client emotion management in financial negotiations

Innovation

• Combines emotion sensing with Game Theory reasoning
• Uses Hidden Markov Models for historical emotion tracking
• Fine-tunes PLMs on emotion datasets for dynamic responses