ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer
Abstract
LLM-based chatbots have improved response quality and reduced costs in customer support, while the experiences of human agents, essential to the service ecosystem, have remained largely overlooked. Stress from harmful texts poses a major challenge for agents, undermining their efficiency, 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. The code related to this paper is available at: https://github.com/sehyeongjo/Proxy-LLM .
Cite
Text
Jo and Seo. "ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025. doi:10.1007/978-3-032-06129-4_28Markdown
[Jo and Seo. "ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025.](https://mlanthology.org/ecmlpkdd/2025/jo2025ecmlpkdd-proxyllm/) doi:10.1007/978-3-032-06129-4_28BibTeX
@inproceedings{jo2025ecmlpkdd-proxyllm,
title = {{ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer}},
author = {Jo, Sehyeong and Seo, Jungwon},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2025},
pages = {444-448},
doi = {10.1007/978-3-032-06129-4_28},
url = {https://mlanthology.org/ecmlpkdd/2025/jo2025ecmlpkdd-proxyllm/}
}