Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Research on Tibetan Tourism Viewpoints information generation system based on LLM

Jinhu Qi, Shuai Yan, Wentao Zhang, Yibo Zhang, Zirui Liu, Ke Wang

TL;DR

This paper tackles the challenge of providing high-quality, structured tourist viewpoint information for Tibet by addressing data sparsity and the need for domain-tailored LLM systems. It introduces the DualGen Bridge AI framework, which fuses a location-keyword extractor with a bridge-based nearest-viewpoint recommender and a generation module, all trained with SFT and LoRA-based fine-tuning, enhanced by ORPO. A novel multi-structure evaluation framework is proposed to assess structured outputs, complemented by empirical validation across dataset construction, keyword extraction, and generation experiments, establishing effective configurations and demonstrating significant improvements in information quality and relevance. The work advances practical, LLM-driven smart tourism for Tibet and lays groundwork for broader, multi-modal, domain-specific tourism information systems. It also offers concrete guidance on parameter-efficient fine-tuning strategies and evaluation methodologies for large-scale language models in resource-constrained, real-world settings.

Abstract

Tibet, ensconced within China's territorial expanse, is distinguished by its labyrinthine and heterogeneous topography, a testament to its profound historical heritage, and the cradle of a unique religious ethos. The very essence of these attributes, however, has impeded the advancement of Tibet's tourism service infrastructure, rendering existing smart tourism services inadequate for the region's visitors. This study delves into the ramifications of informational disparities at tourist sites on Tibetan tourism and addresses the challenge of establishing the Large Language Model (LLM) evaluation criteria. It introduces an innovative approach, the DualGen Bridge AI system, employing supervised fine-tuning techniques to bolster model functionality and enhance optimization processes. Furthermore, it pioneers a multi-structured generative results assessment framework. Empirical validation confirms the efficacy of this framework. The study also explores the application of the supervised fine-tuning method within the proprietary DualGen Bridge AI, aimed at refining the generation of tourist site information. The study's findings offer valuable insights for optimizing system performance and provide support and inspiration for the application of LLM technology in Tibet's tourism services and beyond, potentially revolutionizing the smart tourism industry with advanced, tailored information generation capabilities.

Research on Tibetan Tourism Viewpoints information generation system based on LLM

TL;DR

This paper tackles the challenge of providing high-quality, structured tourist viewpoint information for Tibet by addressing data sparsity and the need for domain-tailored LLM systems. It introduces the DualGen Bridge AI framework, which fuses a location-keyword extractor with a bridge-based nearest-viewpoint recommender and a generation module, all trained with SFT and LoRA-based fine-tuning, enhanced by ORPO. A novel multi-structure evaluation framework is proposed to assess structured outputs, complemented by empirical validation across dataset construction, keyword extraction, and generation experiments, establishing effective configurations and demonstrating significant improvements in information quality and relevance. The work advances practical, LLM-driven smart tourism for Tibet and lays groundwork for broader, multi-modal, domain-specific tourism information systems. It also offers concrete guidance on parameter-efficient fine-tuning strategies and evaluation methodologies for large-scale language models in resource-constrained, real-world settings.

Abstract

Tibet, ensconced within China's territorial expanse, is distinguished by its labyrinthine and heterogeneous topography, a testament to its profound historical heritage, and the cradle of a unique religious ethos. The very essence of these attributes, however, has impeded the advancement of Tibet's tourism service infrastructure, rendering existing smart tourism services inadequate for the region's visitors. This study delves into the ramifications of informational disparities at tourist sites on Tibetan tourism and addresses the challenge of establishing the Large Language Model (LLM) evaluation criteria. It introduces an innovative approach, the DualGen Bridge AI system, employing supervised fine-tuning techniques to bolster model functionality and enhance optimization processes. Furthermore, it pioneers a multi-structured generative results assessment framework. Empirical validation confirms the efficacy of this framework. The study also explores the application of the supervised fine-tuning method within the proprietary DualGen Bridge AI, aimed at refining the generation of tourist site information. The study's findings offer valuable insights for optimizing system performance and provide support and inspiration for the application of LLM technology in Tibet's tourism services and beyond, potentially revolutionizing the smart tourism industry with advanced, tailored information generation capabilities.
Paper Structure (19 sections, 4 equations, 4 figures, 2 tables)

This paper contains 19 sections, 4 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The impact of poor tourist viewpoint information on Tibet’s tourism industry
  3. Current status of application derivation of large-scale language models
  4. Current status of LLM evaluation standards
  5. Related models and Fine-tuning method
  6. Supervised Fine-Tuning - SFT
  7. Optimization - ORPO
  8. Low-Rank Adaptation of Large Language Models - LoRA
  9. DualGen Bridge AI tourist viewpoint information generation system process and implementation
  10. Dataset construction
  11. LLM location information keyword extraction model
  12. Bridge model
  13. LLM tourist viewpoint information generation model
  14. Evaluation criteria for multi-structure generation results
  15. Experiment
  16. ...and 4 more sections

Figures (4)

  • Figure 1: Figure 3-1 DualGen Bridge AI viewpoint information generation system flow chart
  • Figure 2: Data distribution chart of system scoring and manual scoring
  • Figure 3: Zero-Shot vs SFT for Models
  • Figure 4: SFT vs ORPO in Different Computing Type for Models