SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders

2025-04-12

AI Summary

Existing tourism recommendation systems suffer from scarce real-world data, particularly hindering fine-grained personalization for sustainable and off-peak travel. To address this, we propose a knowledge-base-augmented persona-filter joint generation paradigm that leverages large language models (LLMs) to synthesize city-level travel queries exhibiting diversity, personalization, and sustainability orientation. Our method jointly incorporates user personas (e.g., budget, travel style) and structured environmental constraints (e.g., walkability, air quality), while integrating knowledge retrieval to ensure factual controllability. We introduce the first dual-dimension evaluation framework—assessing both realism and alignment—and construct the inaugural synthetic benchmark tailored to sustainable and off-peak tourism. Experiments show 92% of generated queries pass expert authenticity evaluation, and LLM-based automatic assessment significantly outperforms baselines. Our code and dataset are publicly released, and the methodology generalizes to other recommendation domains.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Tourism Recommender Systems (TRS) are crucial in personalizing travel experiences by tailoring recommendations to users' preferences, constraints, and contextual factors. However, publicly available travel datasets often lack sufficient breadth and depth, limiting their ability to support advanced personalization strategies -- particularly for sustainable travel and off-peak tourism. In this work, we explore using Large Language Models (LLMs) to generate synthetic travel queries that emulate diverse user personas and incorporate structured filters such as budget constraints and sustainability preferences. This paper introduces a novel SynthTRIPs framework for generating synthetic travel queries using LLMs grounded in a curated knowledge base (KB). Our approach combines persona-based preferences (e.g., budget, travel style) with explicit sustainability filters (e.g., walkability, air quality) to produce realistic and diverse queries. We mitigate hallucination and ensure factual correctness by grounding the LLM responses in the KB. We formalize the query generation process and introduce evaluation metrics for assessing realism and alignment. Both human expert evaluations and automatic LLM-based assessments demonstrate the effectiveness of our synthetic dataset in capturing complex personalization aspects underrepresented in existing datasets. While our framework was developed and tested for personalized city trip recommendations, the methodology applies to other recommender system domains. Code and dataset are made public at https://bit.ly/synthTRIPs

Problem

• Generating diverse synthetic travel queries for personalized recommendations
• Addressing data gaps in sustainable and off-peak tourism datasets
• Ensuring factual correctness in LLM-generated queries via knowledge grounding

Innovation

• Uses LLMs to generate synthetic travel queries
• Combines persona preferences with sustainability filters
• Grounds LLM responses in knowledge base for accuracy