LLM4Rail: An LLM-Augmented Railway Service Consulting Platform

TL;DR

This paper introduces LLM4Rail, a platform using large language models to enhance personalized railway services through a novel prompting framework and a specialized dataset for onboard dining recommendations.

Contribution

It develops the LLM4Rail platform with the QTAO prompting framework and creates the CRFD-25 dataset for railway food recommendations, advancing personalized railway service solutions.

Findings

Effective integration of reasoning and action in LLMs for railway services

CRFD-25 dataset enables tailored onboard dining recommendations

Zero-shot recommender with feature similarity improves recommendation relevance

Abstract

Large language models (LLMs) have significantly reshaped different walks of business. To meet the increasing demands for individualized railway service, we develop LLM4Rail - a novel LLM-augmented railway service consulting platform. Empowered by LLM, LLM4Rail can provide custom modules for ticketing, railway food & drink recommendations, weather information, and chitchat. In LLM4Rail, we propose the iterative "Question-Thought-Action-Observation (QTAO)" prompting framework. It meticulously integrates verbal reasoning with task-oriented actions, that is, reasoning to guide action selection, to effectively retrieve external observations relevant to railway operation and service to generate accurate responses. To provide personalized onboard dining services, we first construct the Chinese Railway Food and Drink (CRFD-25) - a publicly accessible takeout dataset tailored for railway services. CRFD-25 covers a wide range of signature dishes categorized by cities, cuisines, age groups, and spiciness levels. We further introduce an LLM-based zero-shot conversational recommender for railway catering. To address the unconstrained nature of open recommendations, the feature similarity-based post-processing step is introduced to ensure all the recommended items are aligned with CRFD-25 dataset.