Toward Explainable AI (Part 10): Bridging Theory and Practice—Responsible AI: Ambition or Illusion?

Series reminder: This series explores how explainability in AI helps build trust, ensure accountability, and align with real-world needs, from foundational principles to practical use cases.

Previously, in Part IX: Conclusion: Explainability Under Real-World Conditions: Comparing LIME and SHAP in practice.

In this Part: We take a step back to reflect on the broader requirements of responsible AI: from explainability to governance, ethics, and long-term trust.

Towards Understandable, Useful, and Responsible Artificial Intelligence

In this document, we aimed to follow a logical progression: starting from the theoretical foundations of explainable artificial intelligence to testing the methods on concrete use cases. This interplay between reflection and practice reveals a constant: explainability is not an added luxury but a fundamental criterion of any trustworthy AI.

In the first part, we laid the groundwork: why explainable AI is now an ethical, operational, and regulatory requirement. We explored existing methods, their contributions, limitations, and the contexts where they become critical, such as healthcare, finance, and public services.

In the second part, we dove into the practical side with two detailed experiments using LIME and SHAP. These cases help better understand that explainability not only allows comprehension of a model’s decisions but also helps detect biases, build user trust, and align predictions with human expectations.

But beyond this dual perspective, one conviction emerges: explainable AI is not a state, it is a dynamic process.

A dynamic process made of questioning, adaptations, and dialogues between technical experts, business users, regulators, and citizens. Truly explainable AI does not merely “say why”; it fosters better decision-making, more enlightened governance, and shared responsibility.

It is also worth recalling that building trust through explainable AI goes beyond technical tools and methods. It necessitates robust governance frameworks, clear role assignments, lifecycle integration, and ongoing audits to ensure explainability is effectively operationalized within organizations. Addressing these governance aspects is essential for embedding explainability into AI systems responsibly and sustainably.

Tomorrow, models will be even more powerful but also more complex, hybrid, and ubiquitous. The ability to explain them, without oversimplification or jargon, will be both a strategic challenge and a democratic imperative.

Explainability goes beyond being just a technical tool: it becomes a true shared language between humans and algorithms. This is what it takes to build genuinely collective intelligence.

Wrap-up: Explainability is just one piece of the puzzle. Building responsible AI requires a shift in culture, tools, and accountability. This concludes our series, but the conversation is only beginning.

Links to the previous articles published in this series:

• Toward Explainable AI (Part I): Bridging Theory and Practice—Why AI Needs to Be Explainable
• Toward Explainable AI (Part 2): Bridging Theory and Practice—The Two Major Categories of Explainable AI Techniques
• Toward Explainable AI (Part 3): Bridging Theory and Practice—When Explaining AI Is No Longer a Choice
• Toward Explainable AI (Part 4): Bridging Theory and Practice—Beyond Explainability, What Else Is Needed
• Toward Explainable AI (Part 5): Bridging Theory and Practice—A Hands-On Introduction to LIME
• Toward Explainable AI (Part 6): Bridging Theory and Practice—What LIME Shows – and What It Leaves Out
• Toward Explainable AI (Part 7): Bridging Theory and Practice—SHAP: Bringing Clarity to Financial Decision-Making
• Toward Explainable AI (Part 8): Bridging Theory and Practice—SHAP: Powerful, But Can We Trust It?
• Toward Explainable AI (Part 9): Bridging Theory and Practice—Conclusion: Explainability Under Real-World Conditions

Glossary

Algorithmic Bias: Systematic and unfair discrimination in AI outcomes caused by prejudices embedded in training data, model design, or deployment processes, which can lead to disparate impacts on certain population groups. Detecting and mitigating algorithmic bias is a key objective of explainable AI.

Bias Detection (via XAI): Use of explainability methods to identify biases or disproportionate effects in algorithmic decisions.

Contrastive and Counterfactual Explanations: Explanations that compare the decision made to what could have happened by changing certain variables (e.g., “Why this outcome instead of another?”).

Decision Plot: A graphical representation tracing the successive impact of variables on an individual prediction.

Evaluation Metrics for Explainability: Criteria used to assess the quality of an explanation (fidelity, robustness, consistency, etc.).

Feature Importance (Variable Contribution): Measurement or attribution of the relative impact of each variable on the model’s final decision.

Force Chart (Force Plot): An interactive visualization illustrating positive or negative forces exerted by each variable on a prediction.

Fidelity: A measure of how faithfully the explanation reflects the true logic of the model.

Global Explanation: An overview of the model’s behavior across the entire dataset.

Human Interpretability: The quality of an explanation to be understood and useful to a human, non-expert user.

Intrinsically Interpretable Models: Models whose very structure allows direct understanding (e.g., decision trees, linear regressions).

LIME (Local Interpretable Model-agnostic Explanations): A local explanation method that generates simple approximations around a given prediction to reveal the influential factors.

Local Explanation: A detailed explanation regarding a single prediction or individual case.

Model Transparency: The quality of a model in making its decision-making processes accessible and understandable.

Post-hoc Explainability: Explainability techniques applied after model training, without altering its internal functioning.

Robustness (Stability): The ability of an explainability method to provide consistent explanations despite small variations in input data.

SHAP (SHapley Additive exPlanations): An approach based on game theory that assigns each variable a quantitative contribution to the prediction, providing both global and local explanations.

Summary Chart (Summary Plot): A visualization ranking variables according to their average influence on predictions.

Waterfall Chart: A static visualization showing step by step how each variable contributes to the final prediction.

Links

1. LIME: [link]

2. Chest X-Ray Images (Pneumonia): [link]

3. German Credit Dataset: [link]

4. Complete notebook for the LIME case study: [link] 

5. Complete notebook for the SHAP case study: [link] 

6. Leslie, D., Rincón, C., Briggs, M., Perini, A., Jayadeva, S., Borda, A., et al. (2024). AI Explainability in Practice, The Alan Turing Institute, AI Ethics and Governance in Practice Programme. Participant & Facilitator Workbook: [link]

7. What is AI (Artificial Intelligence)? McKinsey & Company, April 2024 [link]

8. Jennifer Kite-Powell. Explainable AI Is Trending And Here’s Why. Forbes, 2022. Disponible sur: [link]

9. European Commission. Excellence and Trust in AI, European Commission, 2020: [link]

10. Melissa Heikkilä (2024). Nobody really knows how AI works — and that’s a problem. MIT Technology Review: [link]

11. Heaven, W. D. (2023) - Large language models can do jaw-dropping things. But nobody knows exactly why. MIT Technology Review: [link]

12. Forbes - Jameel Francis, “Why 85% of Your AI Models May Fail”, Forbes, 15 Nov. 2024: [link]

13. A. Bao & Y. Zeng, “Understanding the dilemma of explainable artificial intelligence”, Nature -  Humanities and Social Sciences Communication (2024): [link]

14. C. Gallese, The AI Act proposal: a new right to technical interpretability?, arXiv preprint, arXiv:2303.17558 [cs.CY], 2023: [link]

15. European Data Protection Board. (2024). Checklist for AI Auditing Scores – EDPB Support Pool of Experts Programme. June 2024: [link]

16. White, B., & Guha, K. (2025). Component-Based Quantum Machine Learning Explainability. arXiv preprint arXiv:2506.12378: [link]