发表机构
LMU Munich; University of Mannheim（慕尼黑大学; 曼海姆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出利用微调后的大语言模型（LLMs）作为数据转换器的可扩展框架，从非结构化文本生成事件日志，性能远超少样本/零样本提示，为流程挖掘生态系统提供了新的数据利用途径。
AI 中文摘要
流程挖掘（PM）提供了一个强大的框架，可从事件数据中发现和优化运营流程。然而，PM技术的效能严格依赖于结构化事件日志的可用性。迄今为止，事件日志通常由领域专家和流程挖掘专家费力创建，这种高成本的努力导致组织知识的很大一部分（包括事件工单、手册和文本报告）未得到充分利用。我们通过研究大语言模型（LLMs）作为自动化数据转换器的效能来解决这一瓶颈。我们提出了一个可扩展框架，利用LLMs作为数据转换器，弥合非结构化文本资源与结构化事件数据之间的差距。我们在新创建的文本转日志数据集上微调LLMs，证明所得模型可从非结构化资源中提取高保真的事件日志。我们的结果表明，这种微调方法的性能远超少样本或零样本提示，凸显微调是生成可靠事件数据的必要前提。我们得出结论，我们的方法为流程挖掘生态系统提供了一条将先前未使用的数据利用起来的有前景的 pipeline，有效拓展了使用PM进一步研究组织工作流的可能性。
英文摘要
Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM techniques is strictly predicated on the availability of structured event logs. Thus far, event logs have often been laboriously created by domain and process mining experts. This costly effort causes large portions of organizational knowledge, including incident tickets, manuals, and textual reports, to remain underutilized. We address this bottleneck by investigating the efficacy of Large Language Models (LLMs) as automated data translators. We propose a scalable framework that leverages LLMs as data translators to bridge the gap between unstructured textual resources and structured event data. We finetune LLMs on a newly created text-to-log dataset, demonstrating that the resulting models can extract high-fidelity event logs from unstructured resources. Our results show that this finetuning approach outperforms few-shot or zero-shot prompting by a large amount, highlighting finetuning as a necessary pre-condition for generating reliable event data. We conclude that our method provides a promising pipeline for making previously unused data available to process mining ecosystems, effectively expanding the possibilities of using PM to further investigate organizational workflows.
