用大模型提升酒店信息一致性，减少错误描述。
Large Language Models in the Travel Domain: An Industrial Experience
- 用Mixtral和Mistral优化酒店描述生成，减少不一致信息。
- Mixtral准确率98.8%、幻觉率仅1.2%，效果更优。
- 适合关注数据质量与部署成本平衡的工业应用者。
在线酒店预订平台依赖第三方提供的住宿设施信息，但常因数据不全或不一致导致用户体验下降。本文以FERVENTO开发的CALEIDOHOTELS平台为例，评估两种大模型：经QLoRA微调的Mistral 7B和优化提示词的Mixtral 8x7B。前者生成内容完整度93%、精确率96%、幻觉率4%；后者分别达99.6%、98.8%、1.2%，平均文本更短（249字对277字）。但Mixtral需50GB VRAM与每小时$1.61，远高于Mistral的5GB与$0.16。研究揭示了模型性能与资源开销间的权衡，为生产环境部署提供实用参考。
原文摘要 · Abstract (English)
Online property booking platforms are widely used and rely heavily on consistent, up-to-date information about accommodation facilities, often sourced from third-party providers. However, these external data sources are frequently affected by incomplete or inconsistent details, which can frustrate users and result in a loss of market. In response to these challenges, we present an industrial case study involving the integration of Large Language Models (LLMs) into CALEIDOHOTELS, a property reservation platform developed by FERVENTO. We evaluate two well-known LLMs in this context: Mistral 7B, fine-tuned with QLoRA, and Mixtral 8x7B, utilized with a refined system prompt. Both models were assessed based on their ability to generate consistent and homogeneous descriptions while minimizing hallucinations. Mixtral 8x7B outperformed Mistral 7B in terms of completeness (99.6% vs. 93%), precision (98.8% vs. 96%), and hallucination rate (1.2% vs. 4%), producing shorter yet more concise content (249 vs. 277 words on average). However, this came at a significantly higher computational cost: 50GB VRAM and $1.61/hour versus 5GB and $0.16/hour for Mistral 7B. Our findings provide practical insights into the trade-offs between model quality and resource efficiency, offering guidance for deploying LLMs in production environments and demonstrating their effectiveness in enhancing the consistency and reliability of accommodation data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。