Summary of How Well Can a Large Language Model Explain Business Processes As Perceived by Users?, By Dirk Fahland et al.
How well can a large language model explain business processes as perceived by users?
by Dirk Fahland, Fabiana Fournier, Lior Limonad, Inna Skarbovsky, Ava J.E. Swevels
First submitted to arxiv on: 23 Jan 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Large Language Models (LLMs) are revolutionizing businesses by automating various processes, making them a crucial component in future AI-augmented systems. This paper presents the SAX4BPM framework for generating Situation-Aware eXplainability (SAX) explanations. The framework consists of services and a central knowledge repository, which elicit various knowledge ingredients for improved SAX explanations. A key innovation is the causal process execution view. To leverage LLMs’ capabilities, the authors integrated the framework with an LLM to synthesize input ingredients. Despite some concerns about LLMs’ limitations, a methodological evaluation showed that input-assisted LLMs produced better-perceived, faithful explanations, improving trust and curiosity at the cost of interpretability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models are super smart computers that can understand and create human-like text. They’re helping businesses automate tasks and might be used in future systems to make things run more smoothly. This paper is about a special tool called SAX4BPM that helps explain why certain things happened or how they work. The tool uses services and a big database to figure out what makes sense. A key part of this tool is looking at how processes happen. To make it better, the authors connected their tool to an LLM (a really smart computer) so it can understand more information. They tested the tool and found that when they helped the LLM with some information, it made better explanations that people liked. |
