Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.10331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909839569977344 |
|---|---|
| author | Su, Hanchen Luo, Wei Han, Wei Liu, Yu Elaine Zhang, Yufeng Wayne Zhao, Cen Mia Zhang, Ying Joy Mehdad, Yashar |
| author_facet | Su, Hanchen Luo, Wei Han, Wei Liu, Yu Elaine Zhang, Yufeng Wayne Zhao, Cen Mia Zhang, Ying Joy Mehdad, Yashar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Friendly Knowledge Representation for Customer Support Su, Hanchen Luo, Wei Han, Wei Liu, Yu Elaine Zhang, Yufeng Wayne Zhao, Cen Mia Zhang, Ying Joy Mehdad, Yashar Artificial Intelligence 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. |
| title | LLM-Friendly Knowledge Representation for Customer Support |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10331 |