To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning

• URL: http://arxiv.org/abs/2410.16456v1
• Date: Mon, 21 Oct 2024 19:30:05 GMT
• Title: To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
• Authors: Da JU, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine T Kao, Maryam Fazel-Zarandi, Yuandong Tian,
• Abstract summary: To the Globe (TTG) is a real-time demo system that takes natural language requests from users and translates it to symbolic form. The overall system takes 5 seconds to reply to the user request with guaranteed itineraries. When evaluated by users, TTG achieves consistently high Net Promoter Scores (NPS) of 35-40% on generated itinerary.
• Score: 54.9340658451129
• License:
• 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 ~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.

Related papers

• TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners [6.378824981027464]
  Traditional approaches rely on problem formulation in a given formal language. Recent Large Language Model (LLM) based approaches directly output plans from user requests using language. We propose TRIP-PAL, a hybrid method that combines the strengths of LLMs and automated planners.
  arXiv  Detail & Related papers  (2024-06-14T17:31:16Z)
• NATURAL PLAN: Benchmarking LLMs on Natural Language Planning [109.73382347588417]
  We introduce NATURAL PLAN, a realistic planning benchmark in natural language containing 3 key tasks: Trip Planning, Meeting Planning, and Calendar Scheduling. We focus our evaluation on the planning capabilities of LLMs with full information on the task, by providing outputs from tools such as Google Flights, Google Maps, and Google Calendar as contexts to the models.
  arXiv  Detail & Related papers  (2024-06-06T21:27:35Z)
• ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning [17.250579851469695]
  We introduce the novel task of Open-domain Urban Itinerary Planning (OUIP) OUIP generates personalized urban itineraries from user requests in natural language. We present ITINERA, an OUIP system that integrates spatial optimization with large language models to provide customized urban itineraries.
  arXiv  Detail & Related papers  (2024-02-11T13:30:53Z)
• TravelPlanner: A Benchmark for Real-World Planning with Language Agents [63.199454024966506]
  We propose TravelPlanner, a new planning benchmark that focuses on travel planning, a common real-world planning scenario. It provides a rich sandbox environment, various tools for accessing nearly four million data records, and 1,225 meticulously curated planning intents and reference plans. Comprehensive evaluations show that the current language agents are not yet capable of handling such complex planning tasks-even GPT-4 only achieves a success rate of 0.6%.
  arXiv  Detail & Related papers  (2024-02-02T18:39:51Z)
• Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization [126.96113831681338]
  In this paper, we propose to improve zero-shot cross-lingual transfer by composing language or task specialized parameters. Our method composes language and task PEFT modules via element-wise arithmetic operations to leverage unlabeled data and English labeled data.
  arXiv  Detail & Related papers  (2023-11-15T20:04:58Z)
• Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models [47.210211555783836]
  We propose a benchmark named Natural Language Planning and Action (Natala) composed of a set of novel tasks. We find that current popular LLMs such as ChatGPT still lack abilities in complex planning. We propose a novel method called CoS (Chain-of-Symbol Prompting) that represents the complex environments with condensed symbolic spatial representations.
  arXiv  Detail & Related papers  (2023-05-17T15:07:50Z)
• Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification [6.091096843566857]
  We present a learning-based approach for translating from natural language commands to specifications with very limited human-labeled training data. This is in stark contrast to existing natural-language to translators, which require large human-labeled datasets. We show that we can translate natural language commands at 75% accuracy with far less human data.
  arXiv  Detail & Related papers  (2023-03-09T00:09:58Z)
• POIBERT: A Transformer-based Model for the Tour Recommendation Problem [0.3121997724420106]
  We propose POIBERT, an algorithm for recommending personalized itineraries using the BERT language model on POIs. Our recommendation algorithm is able to generate a sequence of POIs that optimize time and users' preference in POI categories based on past trajectories from similar tourists.
  arXiv  Detail & Related papers  (2022-12-16T12:32:15Z)
• Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation [87.03299519917019]
  We propose a dual-scale graph transformer (DUET) for joint long-term action planning and fine-grained cross-modal understanding. We build a topological map on-the-fly to enable efficient exploration in global action space. The proposed approach, DUET, significantly outperforms state-of-the-art methods on goal-oriented vision-and-language navigation benchmarks.
  arXiv  Detail & Related papers  (2022-02-23T19:06:53Z)
• User Preferential Tour Recommendation Based on POI-Embedding Methods [0.624399544884021]
  We propose an algorithm to recommend personalized tours using POI-embedding methods. Our recommendation algorithm will generate a sequence of POIs that optimize time and locational constraints. Preliminary experimental results show that our algorithm is able to recommend a relevant and accurate itinerary.
  arXiv  Detail & Related papers  (2021-03-03T15:18:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.