Just Tell Me: Prompt Engineering in Business Process Management

04/14/2023

∙

GPT-3 and several other language models (LMs) can effectively address various natural language processing (NLP) tasks, including machine translation and text summarization. Recently, they have also been successfully employed in the business process management (BPM) domain, e.g., for predictive process monitoring and process extraction from text. This, however, typically requires fine-tuning the employed LM, which, among others, necessitates large amounts of suitable training data. A possible solution to this problem is the use of prompt engineering, which leverages pre-trained LMs without fine-tuning them. Recognizing this, we argue that prompt engineering can help bring the capabilities of LMs to BPM research. We use this position paper to develop a research agenda for the use of prompt engineering for BPM research by identifying the associated potentials and challenges.

READ FULL TEXT

Just Tell Me: Prompt Engineering in Business Process Management

Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining

A Comparison of SVM against Pre-trained Language Models (PLMs) for Text Classification Tasks

On Cross-Domain Pre-Trained Language Models for Clinical Text Mining: How Do They Perform on Data-Constrained Fine-Tuning?

Large Language Models can accomplish Business Process Management Tasks

Detecting ESG topics using domain-specific language models and data augmentation approaches

MSDT: Masked Language Model Scoring Defense in Text Domain

Sentiment Analysis Challenges in Persian Language

Just Tell Me: Prompt Engineering in Business Process Management

Related Research

Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining

A Comparison of SVM against Pre-trained Language Models (PLMs) for Text Classification Tasks

On Cross-Domain Pre-Trained Language Models for Clinical Text Mining: How Do They Perform on Data-Constrained Fine-Tuning?

Large Language Models can accomplish Business Process Management Tasks

Detecting ESG topics using domain-specific language models and data augmentation approaches

MSDT: Masked Language Model Scoring Defense in Text Domain

Sentiment Analysis Challenges in Persian Language