Iti-Validator: A Guardrail Framework for Validating and Correcting LLM-Generated Itineraries

TL;DR

This paper introduces Iti-Validator, a framework that evaluates and corrects temporal inconsistencies in LLM-generated travel itineraries, enhancing their reliability for practical use.

Contribution

It introduces a validation and correction framework for LLM-generated itineraries, addressing temporal inconsistencies using real-world flight data and improving practical deployment.

Findings

LLMs often produce temporally inconsistent itineraries.

The framework effectively corrects overlapping and unrealistic transit times.

Validated itineraries align better with real-world constraints.

Abstract

The rapid advancement of Large Language Models (LLMs) has enabled them to generate complex, multi-step plans and itineraries. However, these generated plans often lack temporal and spatial consistency, particularly in scenarios involving physical travel constraints. This research aims to study the temporal performance of different LLMs and presents a validation framework that evaluates and improves the temporal consistency of LLM-generated travel itineraries. The system employs multiple state-of-the-art LLMs to generate travel plans and validates them against real-world flight duration constraints using the AeroDataBox API. This work contributes to the understanding of LLM capabilities in handling complex temporal reasoning tasks like itinerary generation and provides a framework to rectify any temporal inconsistencies like overlapping journeys or unrealistic transit times in the itineraries generated by LLMs before the itinerary is given to the user. Our experiments reveal that while current LLMs frequently produce temporally inconsistent itineraries, these can be systematically and reliably corrected using our framework, enabling their practical deployment in large-scale travel planning.