# Automated Event Log Generation from Unstructured Text Using Finetuned LLMs

arXiv: https://arxiv.org/abs/2609.01320 · HTML: https://mlsanity.com/paper/2609.01320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Large Language Models can accomplish Business Process Management Tasks](https://mlsanity.com/paper/2307.09923/) (2023)
- [Abstractions, Scenarios, and Prompt Definitions for Process Mining with LLMs: A Case Study](https://mlsanity.com/paper/2307.02194/) (2023)
- [Evaluating the Ability of LLMs to Solve Semantics-Aware Process Mining Tasks](https://mlsanity.com/paper/2407.02310/) (2024)
- [ProcessTBench: An LLM Plan Generation Dataset for Process Mining](https://mlsanity.com/paper/2409.09191/) (2024)

## Abstract (arXiv)

Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM techniques is strictly predicated on the availability of structured event logs. Thus far, event logs have often been laboriously created by domain and process mining experts. This costly effort causes large portions of organizational knowledge, including incident tickets, manuals, and textual reports, to remain underutilized. We address this bottleneck by investigating the efficacy of Large Language Models (LLMs) as automated data translators. We propose a scalable framework that leverages LLMs as data translators to bridge the gap between unstructured textual resources and structured event data. We finetune LLMs on a newly created text-to-log dataset, demonstrating that the resulting models can extract high-fidelity event logs from unstructured resources. Our results show that this finetuning approach outperforms few-shot or zero-shot prompting by a large amount, highlighting finetuning as a necessary pre-condition for generating reliable event data. We conclude that our method provides a promising pipeline for making previously unused data available to process mining ecosystems, effectively expanding the possibilities of using PM to further investigate organizational workflows.