Business Process Text Sketch Automation Generation Using Large Language Model

TL;DR

This paper introduces a divide-and-conquer approach using Large Language Models to generate business process text sketches from process trees, significantly improving accuracy over traditional prompting methods.

Contribution

It proposes a novel divide-and-conquer prompt strategy with LLMs for transforming complex process trees into text sketches, addressing dataset scarcity issues.

Findings

Achieved 93.42% correctness rate in process text sketch generation.

Outperformed traditional prompting methods by 45.17%.

Demonstrated effectiveness on complex, cyclic, and large process trees.

Abstract

Business Process Management (BPM) is gaining increasing attention as it has the potential to cut costs while boosting output and quality. Business process document generation is a crucial stage in BPM. However, due to a shortage of datasets, data-driven deep learning techniques struggle to deliver the expected results. We propose an approach to transform Conditional Process Trees (CPTs) into Business Process Text Sketches (BPTSs) using Large Language Models (LLMs). The traditional prompting approach (Few-shot In-Context Learning) tries to get the correct answer in one go, and it can find the pattern of transforming simple CPTs into BPTSs, but for close-domain and CPTs with complex hierarchy, the traditional prompts perform weakly and with low correctness. We suggest using this technique to break down a difficult CPT into a number of basic CPTs and then solve each one in turn, drawing inspiration from the divide-and-conquer strategy. We chose 100 process trees with depths ranging from 2 to 5 at random, as well as CPTs with many nodes, many degrees of selection, and cyclic nesting. Experiments show that our method can achieve a correct rate of 93.42%, which is 45.17% better than traditional prompting methods. Our proposed method provides a solution for business process document generation in the absence of datasets, and secondly, it becomes potentially possible to provide a large number of datasets for the process model extraction (PME) domain.