SAX4BPM User Study Data

该数据集是通过在线问卷调查收集的，旨在评估大规模语言模型在不同商业流程领域生成的解释质量，这些领域包括披萨外卖、停车罚款和贷款审批。数据集还包括了根据不同业务流程提供的解释，与人口统计信息相关的数据以及关于忠实度、可解释性、好奇心和信任度的反馈。所使用的量表为李克特量表（1-7分制）。该任务的目标是针对地面真实解释，评估由大型语言模型生成的解释的质量。

This dataset was collected via online questionnaires, aiming to evaluate the quality of explanations generated by large language models (LLMs) across different business process domains including pizza delivery, parking fines, and loan approval. The dataset also includes explanations tailored to various business workflows, data related to demographic information, and feedback regarding fidelity, explainability, curiosity, and trust. The scale adopted is the 7-point Likert scale. The core objective of this task is to assess the quality of explanations produced by large language models against ground-truth explanations.