ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer

TL;DR

ProxyLLM addresses the emotional burden of customer support agents by using LLM-driven text-style transfer to soften the tone of customer messages while preserving actionable content. The system is designed to mitigate emotional exhaustion and improve overall service experience for agents, customers, and businesses, and is implemented as a Chrome extension for easy integration. By focusing on tone transformation rather than content loss, it aims to reduce burnout without sacrificing task-oriented information. The work highlights practical implications for agent well-being and service quality in real-world support workflows, enabling safer, more sustainable human-AI collaboration in customer service.

Abstract

Chatbot-based customer support services have significantly advanced with the introduction of large language models (LLMs), enabling enhanced response quality and broader application across industries. However, while these advancements focus on reducing business costs and improving customer satisfaction, limited attention has been given to the experiences of customer service agents, who are critical to the service ecosystem. A major challenge faced by agents is the stress caused by unnecessary emotional exhaustion from harmful texts, which not only impairs their efficiency but also negatively affects customer satisfaction and business outcomes. In this work, we propose an LLM-powered system designed to enhance the working conditions of customer service agents by addressing emotionally intensive communications. Our proposed system leverages LLMs to transform the tone of customer messages, preserving actionable content while mitigating the emotional impact on human agents. Furthermore, the application is implemented as a Chrome extension, making it highly adaptable and easy to integrate into existing systems. Our method aims to enhance the overall service experience for businesses, customers, and agents.