Metraipolis › archive › dc_cdccf5cc5189

Automated Event Log Generation from Unstructured Text Using Finetuned LLMs — arXiv:2609.01320

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01320
License (as archived): CC0-1.0
Archived: 2026-10-17T06:32:25.915Z
SHA-256 of the archived text: 7c089a3c4e1de3e82d9dcf6d160843c781946629ec7175a11033aae25324e4ce
Stable URL of this page: https://metraipolis.com/documento/dc_cdccf5cc5189

How to cite

Automated Event Log Generation from Unstructured Text Using Finetuned LLMs — arXiv:2609.01320 — arXiv (en), https://arxiv.org/abs/2609.01320 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdccf5cc5189 (Metraipolis archive dc_cdccf5cc5189, sha256 7c089a3c4e1de3e82d9dcf6d160843c781946629ec7175a11033aae25324e4ce)

BibTeX

@misc{dccdccf5cc5189,
  title = {Automated Event Log Generation from Unstructured Text Using Finetuned LLMs — arXiv:2609.01320},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01320},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdccf5cc5189; sha256 7c089a3c4e1de3e82d9dcf6d160843c781946629ec7175a11033aae25324e4ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01320. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01320 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.688Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).