RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization

2024-08-21

arXiv.org

AI Summary

Large language models (LLMs) exhibit weak personalization and severe hallucination when deployed for tourism recommendation in Tibet. Method: This work constructs a scenic-spot knowledge vector database tailored to Tibetan cultural and tourism domains and pioneers the systematic application of retrieval-augmented generation (RAG) in this vertical field. It integrates Sentence-BERT/FAISS-based text vectorization, domain-specific knowledge base construction, LLM fine-tuning, and prompt engineering to jointly optimize retrieval accuracy and hallucination suppression. Contribution/Results: Experiments demonstrate a 32.7% improvement in retrieval accuracy and a reduction in hallucination rate to below 5%, significantly enhancing output accuracy, relevance, and fluency. The framework advances standardization of cultural-tourism information and enables practical intelligent services, establishing a reusable technical paradigm and empirical validation for RAG deployment in domain-specific applications.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Summarization

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the development of the modern social economy, tourism has become an important way to meet people's spiritual needs, bringing development opportunities to the tourism industry. However, existing large language models (LLMs) face challenges in personalized recommendation capabilities and the generation of content that can sometimes produce hallucinations. This study proposes an optimization scheme for Tibet tourism LLMs based on retrieval-augmented generation (RAG) technology. By constructing a database of tourist viewpoints and processing the data using vectorization techniques, we have significantly improved retrieval accuracy. The application of RAG technology effectively addresses the hallucination problem in content generation. The optimized model shows significant improvements in fluency, accuracy, and relevance of content generation. This research demonstrates the potential of RAG technology in the standardization of cultural tourism information and data analysis, providing theoretical and technical support for the development of intelligent cultural tourism service systems.

Problem

• Enhancing personalized recommendation capabilities
• Reducing hallucinations in content generation
• Improving retrieval accuracy for tourism data

Innovation

• RAG technology optimization
• Vectorized data processing
• Enhanced content accuracy