Metraipolis › archive › dc_9fcefc70bb2f

D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoring — arXiv:2608.28236

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28236
License (as archived): CC0-1.0
Archived: 2026-10-17T11:06:34.251Z
SHA-256 of the archived text: 597fba62fd780f95130a32a4c82f5c02417efd5b952700d7a494b1c4ec7f574e
Stable URL of this page: https://metraipolis.com/documento/dc_9fcefc70bb2f

How to cite

D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoring — arXiv:2608.28236 — arXiv (en), https://arxiv.org/abs/2608.28236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fcefc70bb2f (Metraipolis archive dc_9fcefc70bb2f, sha256 597fba62fd780f95130a32a4c82f5c02417efd5b952700d7a494b1c4ec7f574e)

BibTeX

@misc{dc9fcefc70bb2f,
  title = {D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoring — arXiv:2608.28236},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28236},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fcefc70bb2f; sha256 597fba62fd780f95130a32a4c82f5c02417efd5b952700d7a494b1c4ec7f574e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predictive Process Monitoring (PPM) enables organizations to forecast future process behavior, such as the next activity and remaining time of ongoing cases. In practice, three conditions cause existing methods to degrade, namely data scarcity, high process entropy and distributional shift. While Foundation Models (FMs), especially Large Language Models (LLMs), offer a new paradigm through broad sequential reasoning, adapting them to multi-task PPM under these conditions remains an open challenge. Existing FM-based approaches either lack mechanisms for handling distributional shift or rely on direct regression heads that can be structurally misaligned with continuous time prediction tasks. This paper introduces D-TAIA (Domain-aware Training and Attention-based Inference Architecture), a framework for a joint next activity and remaining time prediction task via parameter-efficient fine-tuning of an FM backbone. Our approach combines domain-aware triplet loss (DATL) pre-training with FAISS-based nearest neighbor retrieval for remaining time prediction, and adopts the TAIA inference strategy to preserve pre-trained sequential reasoning during fine-tuning. Evaluated across four real-world event logs, D-TAIA consistently shows SOTA or competitive performance compared to a fine-tuned LLM and a recurrent neural network baseline. Ablation studies confirm that techniques from NLP and computer vision can be transferred effectively to PPM with only a 10M-parameter backbone, though component contributions vary by dataset entropy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.28236 — 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 2026-10-17T10:50:25.803Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).