Large Language Models in the Travel Domain: An Industrial Experience
This addresses data quality issues for travel platforms, but it is an incremental application of existing LLMs to a specific domain.
The study tackled incomplete and inconsistent accommodation data in online booking platforms by evaluating two LLMs (Mistral 7B and Mixtral 8x7B) for generating descriptions, finding that Mixtral 8x7B outperformed in completeness (99.6% vs. 93%), precision (98.8% vs. 96%), and hallucination rate (1.2% vs. 4%) but at higher computational costs.
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.