Saved in:
Bibliographic Details
Main Authors: JU, Da, Jiang, Song, Cohen, Andrew, Foss, Aaron, Mitts, Sasha, Zharmagambetov, Arman, Amos, Brandon, Li, Xian, Kao, Justine T, Fazel-Zarandi, Maryam, Tian, Yuandong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.16456
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909358814658560
author JU, Da
Jiang, Song
Cohen, Andrew
Foss, Aaron
Mitts, Sasha
Zharmagambetov, Arman
Amos, Brandon
Li, Xian
Kao, Justine T
Fazel-Zarandi, Maryam
Tian, Yuandong
author_facet JU, Da
Jiang, Song
Cohen, Andrew
Foss, Aaron
Mitts, Sasha
Zharmagambetov, Arman
Amos, Brandon
Li, Xian
Kao, Justine T
Fazel-Zarandi, Maryam
Tian, Yuandong
contents 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 ~5 seconds to reply to the user request with guaranteed itineraries. To train TTG, we develop a synthetic data pipeline that generates user requests, 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 ~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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16456
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
JU, Da
Jiang, Song
Cohen, Andrew
Foss, Aaron
Mitts, Sasha
Zharmagambetov, Arman
Amos, Brandon
Li, Xian
Kao, Justine T
Fazel-Zarandi, Maryam
Tian, Yuandong
Computation and Language
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 ~5 seconds to reply to the user request with guaranteed itineraries. To train TTG, we develop a synthetic data pipeline that generates user requests, 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 ~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.
title To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
topic Computation and Language
url https://arxiv.org/abs/2410.16456