# Large Language Models in the Travel Domain: An Industrial Experience

arXiv: https://arxiv.org/abs/2507.22910 · HTML: https://mlsanity.com/paper/2507.22910/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [Fine-tuning Large Language Models for Adaptive Machine Translation](https://mlsanity.com/paper/2312.12740/) (2023)
- [Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions](https://mlsanity.com/paper/2404.09135/) (2024)
- [CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge](https://mlsanity.com/paper/2407.12791/) (2024)
- [TourBERT: A pretrained language model for the tourism industry](https://mlsanity.com/paper/2201.07449/) (2022)

## Abstract (arXiv)

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.