Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.09732 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909836860456960 |
|---|---|
| author | van Oerle, P. Bemthuis, R. H. Bukhsh, F. A. |
| author_facet | van Oerle, P. Bemthuis, R. H. Bukhsh, F. A. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09732 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction van Oerle, P. Bemthuis, R. H. Bukhsh, F. A. Machine Learning Artificial Intelligence 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. |
| title | Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.09732 |