PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks

TL;DR

This paper introduces PM-LLM-Benchmark, a comprehensive evaluation framework for assessing large language models' capabilities in process mining tasks, highlighting current strengths and limitations of open-source models.

Contribution

It presents the first dedicated benchmark for process mining with LLMs, addressing domain-specific knowledge and implementation strategies, and discusses challenges in evaluation and data availability.

Findings

Most LLMs perform adequately on process mining tasks

Tiny models are still inadequate for edge device deployment

Evaluation biases affect the ranking of LLMs in process mining

Abstract

Large Language Models (LLMs) have the potential to semi-automate some process mining (PM) analyses. While commercial models are already adequate for many analytics tasks, the competitive level of open-source LLMs in PM tasks is unknown. In this paper, we propose PM-LLM-Benchmark, the first comprehensive benchmark for PM focusing on domain knowledge (process-mining-specific and process-specific) and on different implementation strategies. We focus also on the challenges in creating such a benchmark, related to the public availability of the data and on evaluation biases by the LLMs. Overall, we observe that most of the considered LLMs can perform some process mining tasks at a satisfactory level, but tiny models that would run on edge devices are still inadequate. We also conclude that while the proposed benchmark is useful for identifying LLMs that are adequate for process mining tasks, further research is needed to overcome the evaluation biases and perform a more thorough ranking of the competitive LLMs.