Life of Research
Appearance

Faithful, Robust, Uncertainty-Aware and Human-Centred Explanations for High-Stakes Machine Learning Systems

  • Dominic Namachila
  1. University of Cape Town

Thesis / Dissertation

LOR-00208

Download PDF (417.2 KB) Cite

Cite

Faithful, Robust, Uncertainty-Aware and Human-Centred Explanations for High-Stakes Machine Learning Systems

Read

Abstract

Machine learning systems now inform decisions in medicine, finance, justice and public administration, yet the most accurate models are frequently opaque, brittle under distribution shift, and unevenly reliable across population groups. Explainable AI (XAI) promises to close the gap between predictive performance and warranted human trust, but a growing body of evidence shows that popular explanation methods can be unfaithful to the model, unstable under small perturbations, manipulable by adversaries, and of limited help to the people who must act on them. This thesis argues that explainability and trustworthiness must be studied as a single, jointly evaluated problem rather than as separate add-ons to a trained model.

The thesis makes four contributions. First, it proposes a conceptual framework that links explanation properties (fidelity, stability, comprehensibility, actionability) to trustworthiness pillars (robustness, calibrated uncertainty, fairness, accountability) and to stakeholder needs. Second, it develops a methodology for training and evaluating faithful and stable feature attributions. Third, it introduces uncertainty-aware explanations that report how confident the model, and the explanation itself, are. Fourth, it designs a human-centred evaluation protocol, including fairness-oriented audits and controlled user studies, to measure whether explanations improve appropriate reliance rather than merely increasing confidence. The thesis closes with an integrated assessment toolkit and a discussion of regulatory alignment with the EU AI Act and the NIST AI Risk Management Framework.

Keywords

Files (1)

Cite this record

Namachila, D. (2025). Faithful, Robust, Uncertainty-Aware and Human-Centred Explanations for High-Stakes Machine Learning Systems [Thesis]. Life of Research. https://lifeofresearch.com/theses/208

APA 7th edition
Export to a reference manager
BibTeX
@phdthesis{namachila2025faithful,
  author       = {Namachila, Dominic},
  title        = {{Faithful, Robust, Uncertainty-Aware and Human-Centred Explanations for High-Stakes Machine Learning Systems}},
  year         = {2025},
  month        = sep,
  date         = {2025-09-11},
  type         = {Thesis},
  url          = {https://lifeofresearch.com/theses/208},
  abstract     = {Machine learning systems now inform decisions in medicine, finance, justice and public administration, yet the most accurate models are frequently opaque, brittle under distribution shift, and unevenly reliable across population groups. Explainable AI (XAI) promises to close the gap between predictive performance and warranted human trust, but a growing body of evidence shows that popular explanation methods can be unfaithful to the model, unstable under small perturbations, manipulable by adversaries, and of limited help to the people who must act on them. This thesis argues that explainability and trustworthiness must be studied as a single, jointly evaluated problem rather than as separate add-ons to a trained model.

The thesis makes four contributions. First, it proposes a conceptual framework that links explanation properties (fidelity, stability, comprehensibility, actionability) to trustworthiness pillars (robustness, calibrated uncertainty, fairness, accountability) and to stakeholder needs. Second, it develops a methodology for training and evaluating faithful and stable feature attributions. Third, it introduces uncertainty-aware explanations that report how confident the model, and the explanation itself, are. Fourth, it designs a human-centred evaluation protocol, including fairness-oriented audits and controlled user studies, to measure whether explanations improve appropriate reliance rather than merely increasing confidence. The thesis closes with an integrated assessment toolkit and a discussion of regulatory alignment with the EU AI Act and the NIST AI Risk Management Framework.},
  keywords     = {explainable AI, trustworthy AI, interpretability, faithfulness, uncertainty quantification, fairness, human-AI interaction, AI governance.},
  language     = {en},
  copyright    = {Creative Commons Attribution 4.0}
}

Using Zotero or Mendeley? Their browser connector saves this record from this page, with its PDF when there is one. On search and browse pages it lists every result so you can save many at once.

Guides What a complete citation needs What CC BY 4.0 allows