Researchers have developed a new framework that uses finetuned Large Language Models (LLMs) to automatically generate structured event logs from unstructured text. This method addresses the bottleneck of manual event log creation, which often leaves valuable organizational knowledge in documents like incident tickets and reports underutilized. By finetuning LLMs on a newly created text-to-log dataset, the models can extract high-fidelity event logs, significantly outperforming zero-shot or few-shot prompting and making previously inaccessible data available for process mining. AI
IMPACT Enables broader application of process mining by unlocking unstructured data sources for workflow analysis.
RANK_REASON The cluster contains an academic paper detailing a new method for using LLMs in process mining. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- large-language models
- process mining
- ScienceCast
- text-to-log dataset
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
