From Theory to Practice: Real-World Use Cases on Trustworthy LLM-Driven Process Modeling, Prediction and Automation

2025-06-04

AI Summary

Traditional Business Process Management (BPM) suffers from rigidity, opacity, and poor scalability in dynamic environments. Method: This paper proposes a trustworthy process intelligence augmentation paradigm that integrates uncertainty-aware interpretable machine learning, knowledge graph–enhanced large language models (LLMs), multi-agent systems, and BPMN semantic parsing to construct a context-sensitive, value-aligned, human-AI collaborative LLM integration framework. Contribution/Results: Evaluated across four industrial use cases—manufacturing forecasting, BPMN dialogue modeling, pharmacovigilance monitoring, and sustainable textile design—the framework enables auditable predictions, zero-code process modeling, automated drug safety surveillance, and compliance-aware eco-design. Empirical results demonstrate the feasibility and effectiveness of human-in-the-loop, trustworthy LLM-driven process modeling, prediction, and automation. This work establishes the first systematic, end-to-end pathway for integrating trustworthy LLMs with BPM in dynamic business contexts.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Intelligent Query Processing
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Traditional Business Process Management (BPM) struggles with rigidity, opacity, and scalability in dynamic environments while emerging Large Language Models (LLMs) present transformative opportunities alongside risks. This paper explores four real-world use cases that demonstrate how LLMs, augmented with trustworthy process intelligence, redefine process modeling, prediction, and automation. Grounded in early-stage research projects with industrial partners, the work spans manufacturing, modeling, life-science, and design processes, addressing domain-specific challenges through human-AI collaboration. In manufacturing, an LLM-driven framework integrates uncertainty-aware explainable Machine Learning (ML) with interactive dialogues, transforming opaque predictions into auditable workflows. For process modeling, conversational interfaces democratize BPMN design. Pharmacovigilance agents automate drug safety monitoring via knowledge-graph-augmented LLMs. Finally, sustainable textile design employs multi-agent systems to navigate regulatory and environmental trade-offs. We intend to examine tensions between transparency and efficiency, generalization and specialization, and human agency versus automation. By mapping these trade-offs, we advocate for context-sensitive integration prioritizing domain needs, stakeholder values, and iterative human-in-the-loop workflows over universal solutions. This work provides actionable insights for researchers and practitioners aiming to operationalize LLMs in critical BPM environments.

Problem

• Addressing rigidity and opacity in traditional Business Process Management (BPM)
• Exploring trustworthy LLM-driven process modeling and automation solutions
• Balancing transparency, efficiency, and human-AI collaboration in BPM

Innovation

• LLM-driven framework integrates uncertainty-aware ML
• Conversational interfaces democratize BPMN design
• Knowledge-graph-augmented LLMs automate drug monitoring