Paper Summaries

Just Tell Me: Prompt Engineering in Business Process Management - Summary

The paper discusses the use of prompt engineering to leverage pre-trained language models for business process management (BPM) tasks. It identifies the potentials and challenges of prompt engineering for BPM research.

Arxiv URL: https://arxiv.org/abs/2304.07183

Authors: Kiran Busch, Alexander Rochlitzer, Diana Sola, Henrik Leopold

Summary:

The paper discusses the use of prompt engineering to leverage pre-trained language models for business process management (BPM) tasks. It identifies the potentials and challenges of prompt engineering for BPM research.

Key Insights & Learnings:

Pre-trained language models (LMs) can be effectively used for various natural language processing (NLP) tasks, including BPM tasks.
Fine-tuning LMs for BPM tasks requires large amounts of suitable training data, which is a common issue in BPM practice.
Prompt engineering can help address the issue of limited downstream data and yield promising results in various NLP tasks.
Prompt engineering involves the use of natural language task specifications, known as prompts, which are given to the LM at inference time to provide it with information about the downstream task.
Prompt engineering has the potential to effectively address a large variety of NLP-related BPM tasks and reduce the need for highly specialized and use-case-specific techniques as well as the need to obtain large training datasets.

Terms Mentioned: natural language processing, business process management, language models, fine-tuning, prompt engineering, downstream data, inference time, task specifications, in-context learning, prompt templates

Technologies / Libraries Mentioned: GPT-3, transformer architecture

Instruction Tuning with GPT-4 - Summary

The paper presents the first attempt to use GPT-4 to generate instruction-following data for Large Language Models (LLMs) finetuning. The 52K English and Chinese instruction-following data generated by GPT-4 leads to superior zero-shot performance on new tasks compared to the instruction-following

Are We Really Making Much Progress in Text Classification? A Comparative Review - Summary

This paper reviews and compares methods for single-label and multi-label text classification, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical methods. The findings reveal that pre-trained language models outperform all recently proposed graph-based and hierarchy-b

A Survey of Large Language Models - Summary

This paper surveys the recent advances in Large Language Models (LLMs), which are pre-trained Transformer models over large-scale corpora. The paper discusses the background, key findings, and mainstream techniques of LLMs, focusing on pre-training, adaptation tuning, utilization, and capacity eval

Read next