Fine-tuning small LLMs on raw process data with parameter-efficient methods improves predictive process monitoring, with the clearest gains in multi-task remaining-time prediction.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Domain Adaptation of LLMs for Process Data
Fine-tuning small LLMs on raw process data with parameter-efficient methods improves predictive process monitoring, with the clearest gains in multi-task remaining-time prediction.