We propose a practical approach by integrating Large Language Models (LLMs) with a framework designed to navigate the complexities of Airbnb customer support operations. In this paper, our methodology employs a novel reformatting technique, the Intent, Context, and Action (ICA) format, which transforms policies and workflows into a structure more comprehensible to LLMs. Additionally, we develop a synthetic data generation strategy to create training data with minimal human intervention, enabling cost-effective fine-tuning of our model. Our internal experiments (not applied to Airbnb products) demonstrate that our approach of restructuring workflows and fine-tuning LLMs with synthetic data significantly enhances their performance, setting a new benchmark for their application in customer support. Our solution is not only cost-effective but also improves customer support, as evidenced by both accuracy and manual processing time evaluation metrics.
@article{arxiv.2510.10331,
title = {LLM-Friendly Knowledge Representation for Customer Support},
author = {Hanchen Su and Wei Luo and Wei Han and Yu Elaine Liu and Yufeng Wayne Zhang and Cen Mia Zhao and Ying Joy Zhang and Yashar Mehdad},
journal= {arXiv preprint arXiv:2510.10331},
year = {2025}
}