@inproceedings{ju-etal-2024-globe,
    title = "To the Globe ({TTG}): Towards Language-Driven Guaranteed Travel Planning",
    author = "Ju, Da  and
      Jiang, Song  and
      Cohen, Andrew  and
      Foss, Aaron  and
      Mitts, Sasha  and
      Zharmagambetov, Arman  and
      Amos, Brandon  and
      Li, Xian  and
      Kao, Justine T  and
      Fazel-Zarandi, Maryam  and
      Tian, Yuandong",
    editor = "Hernandez Farias, Delia Irazu  and
      Hope, Tom  and
      Li, Manling",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-demo.25/",
    doi = "10.18653/v1/2024.emnlp-demo.25",
    pages = "240--249",
    abstract = "Travel planning is a challenging and time-consuming task that aims to find an itinerary which satisfies multiple, interdependent constraints regarding flights, accommodations, attractions, and other travel arrangements. In this paper, we propose To the Globe (TTG), a real-time demo system that takes natural language requests from users, translates it to symbolic form via a fine-tuned Large Language Model, and produces optimal travel itineraries with Mixed Integer Linear Programming solvers. The overall system takes {\textasciitilde}5seconds to reply to the user request with guaranteed itineraries. To train TTG, we develop a synthetic data pipeline that generates userrequests, flight and hotel information in symbolic form without human annotations, based on the statistics of real-world datasets, and fine-tune an LLM to translate NL user requests to their symbolic form, which is sent to the symbolic solver to compute optimal itineraries. Our NL-symbolic translation achieves {\textasciitilde}91{\%} exact match in a backtranslation metric (i.e., whether the estimated symbolic form of generated natural language matches the groundtruth), and its returned itineraries have a ratio of 0.979 compared to the optimal cost of the ground truth user request. When evaluated by users, TTG achieves consistently high Net Promoter Scores (NPS) of 35-40{\%} on generated itinerary."
}