Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Paul Darm, Cem Alpturk, Kenneth Ulrich, William Duncan, Ali Anwar, Annalisa Riccardi
• Venue: arXiv: cs.AI
• Published: 2026-07-16
• Collected: 2026-07-17
• URL: http://arxiv.org/abs/2607.14970v1
• PDF: https://arxiv.org/pdf/2607.14970v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers propose a method to explain optimisation recommendations for industrial processes using Shapley Additive exPlanations (SHAP), Implicit Function Theorem, and Large Language Models (LLM). The new approach calculates parameter sensitivities more efficiently, achieving a 40x speedup for an HPGR control optimisation problem. They validate their method on industrial scenarios and gather feedback from domain experts.

What the Document Says

• The paper presents a method that integrates Implicit Function Theorem (IFT) based sensitivity analysis with SHAP attribution and narrative generation via Large Language Models.
• The approach leverages IFT to compute exact parameter sensitivities and enable efficient GradientSHAP computation.
• For an industrial High Pressure Grinding Roll (HPGR) control optimisation problem, the new method achieves equivalent SHAP attributions with over 40x speedup compared to KernelSHAP.
• The researchers validate their approach on industrial scenarios and gather feedback from domain experts on generated explanations.

Key Concepts Mentioned

• automated optimization
• industrial processes
• explainable AI
• SHAP (SHapley Additive exPlanations)
• Implicit Function Theorem (IFT)
• Large Language Models (LLM)
• parameter sensitivities
• GradientSHAP
• High Pressure Grinding Roll (HPGR)

Claims Made by the Document

• The proposed method can produce explanations tailored for operators.
• The new approach achieves equivalent SHAP attributions with over 40x speedup compared to KernelSHAP for an HPGR control optimisation problem.

Evidence Used

• The paper describes the method and its integration of IFT, SHAP, and LLM
• The researchers provide results showing equivalent SHAP attributions and speedup comparison with KernelSHAP

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their recommendations. Explainable AI methods like SHAP (SHapley Additive exPlanations) have transformed interpretability for machine learning predictions; optimisation outputs could benefit from similar techniques. We present an approach that integrates Implicit Function Theorem (IFT) based sensitivity analysis with SHAP attribution and narrative generation via Large Language Models (LLM), producing explanations tailored for operators. Our approach leverages IFT to compute exact parameter sensitivities $\partial p^*/\partial x$ from the optimality conditions, enabling efficient GradientSHAP computation. For an industrial High Pressure Grinding Roll (HPGR) control optimisation problem with 22 features, we achieve equivalent SHAP attributions (correlation $>$0.99 with KernelSHAP) with over 40$\times$ speedup, enabling real-time natural language explanations. We validate on industrial scenarios and present feedback from domain experts on generated explanations.