Saved in:
Bibliographic Details
Main Authors: Liu, Yunuo, Zhu, Dawei, Al-Khalili, Zena, Cheng, Dai, Chen, Yanjun, Klakow, Dietrich, Zhang, Wei, Shen, Xiaoyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.12409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912646090981376
author Liu, Yunuo
Zhu, Dawei
Al-Khalili, Zena
Cheng, Dai
Chen, Yanjun
Klakow, Dietrich
Zhang, Wei
Shen, Xiaoyu
author_facet Liu, Yunuo
Zhu, Dawei
Al-Khalili, Zena
Cheng, Dai
Chen, Yanjun
Klakow, Dietrich
Zhang, Wei
Shen, Xiaoyu
contents We present PricingLogic, the first benchmark that probes whether Large Language Models(LLMs) can reliably automate tourism-related prices when multiple, overlapping fare rules apply. Travel agencies are eager to offload this error-prone task onto AI systems; however, deploying LLMs without verified reliability could result in significant financial losses and erode customer trust. PricingLogic comprises 300 natural-language questions based on booking requests derived from 42 real-world pricing policies, spanning two levels of difficulty: (i) basic customer-type pricing and (ii)bundled-tour calculations involving interacting discounts. Evaluations of a line of LLMs reveal a steep performance drop on the harder tier,exposing systematic failures in rule interpretation and arithmetic reasoning.These results highlight that, despite their general capabilities, today's LLMs remain unreliable in revenue-critical applications without further safeguards or domain adaptation. Our code and dataset are available at https://github.com/EIT-NLP/PricingLogic.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12409
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
Liu, Yunuo
Zhu, Dawei
Al-Khalili, Zena
Cheng, Dai
Chen, Yanjun
Klakow, Dietrich
Zhang, Wei
Shen, Xiaoyu
Artificial Intelligence
We present PricingLogic, the first benchmark that probes whether Large Language Models(LLMs) can reliably automate tourism-related prices when multiple, overlapping fare rules apply. Travel agencies are eager to offload this error-prone task onto AI systems; however, deploying LLMs without verified reliability could result in significant financial losses and erode customer trust. PricingLogic comprises 300 natural-language questions based on booking requests derived from 42 real-world pricing policies, spanning two levels of difficulty: (i) basic customer-type pricing and (ii)bundled-tour calculations involving interacting discounts. Evaluations of a line of LLMs reveal a steep performance drop on the harder tier,exposing systematic failures in rule interpretation and arithmetic reasoning.These results highlight that, despite their general capabilities, today's LLMs remain unreliable in revenue-critical applications without further safeguards or domain adaptation. Our code and dataset are available at https://github.com/EIT-NLP/PricingLogic.
title PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
topic Artificial Intelligence
url https://arxiv.org/abs/2510.12409