# Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction

arXiv: https://arxiv.org/abs/2510.09732 · HTML: https://mlsanity.com/paper/2510.09732/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Large Language Models can accomplish Business Process Management Tasks](https://mlsanity.com/paper/2307.09923/) (2023)
- [Process Mining for Python (PM4Py): Bridging the Gap Between Process- and Data Science](https://mlsanity.com/paper/1905.06169/) (2019)
- [History, Development, and Principles of Large Language Models-An Introductory Survey](https://mlsanity.com/paper/2402.06853/) (2024)
- [PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks](https://mlsanity.com/paper/2407.13244/) (2024)
- [Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks](https://mlsanity.com/paper/2407.02310/) (2024)
- [Chit-Chat or Deep Talk: Prompt Engineering for Process Mining](https://mlsanity.com/paper/2307.09909/) (2023)
- [Leveraging Large Language Models (LLMs) for Process Mining (Technical Report)](https://mlsanity.com/paper/2307.12701/) (2023)
- [A Process Mining Software Comparison](https://mlsanity.com/paper/2007.14038/) (2020)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs or Petri nets) can be computationally expensive. This paper reports an exploratory evaluation of explanation quality under progressive behavioral-input reduction, where models are discovered from progressively smaller prefixes of a fixed log. Our pipeline (i) discovers models at multiple input sizes, (ii) prompts an LLM to generate explanations, and (iii) uses a second LLM to assess completeness, bottleneck identification, and suggested improvements. On synthetic logs, explanation quality is largely preserved under moderate reduction, indicating a practical cost-quality trade-off. The study is exploratory, as the scores are LLM-based (comparative signals rather than ground truth) and the data are synthetic. The results suggest a path toward more computationally efficient, LLM-assisted process analysis in resource-constrained settings.