Abstract: Artificial Intelligence (AI) has become an integral part of our society: we have smart assistants with speech recognition on our phones, self-driving cars, and online algorithms that recommend what we should buy, watch or listen to. Most of these AI systems learn to make decisions based on data: large quantities of examples from the past. The exact internal reasoning of such AI systems that learn from data is difficult to determine, however. This can cause the AI system to behave irresponsibly.

In this thesis, we introduce a method to evaluate the internal reasoning of AI systems that learn from data. We show that AI systems sometimes make the right decisions, but for the wrong reasons. For example, unbeknownst to us, an AI system can learn an undesirable, hidden bias from the data.

The method that we describe in our thesis can not only evaluate the internal reasoning of an AI system, but can also adjust it and steer it in the right direction. Additionally, we also show how one can create an AI system with predefined reasoning, rather than making it learn its reasoning from data. This way, the system cannot accidentally learn to make the decisions for the wrong reasons.

All of the methods we discuss in the thesis build upon the idea that we should use the domain knowledge of human experts when designing AI systems that learn from data. The thesis shows that this is essential for designing responsible artificial intelligence.

Publications:

• Taking the law more seriously by investigating design choices in machine learning prediction research In: ASAIL 2023. Automated Semantic Analysis of Information in Legal Text. Proceedings of the 6th Workshop on Automated Semantic Analysis of Information in Legal Text co-located with the 19th International Conference on Artificial Intelligence and Law (ICAIL 2023), pp. 49–59, CEUR-WS, Braga, Portugal, 2023.
• Improving rationales with small, inconsistent and incomplete data In: Sileno, G.; Spanakis, J.; van Dijck, G. (Ed.): Legal Knowledge and Information Systems – JURIX 2023: The Thirty-Sixth Annual Conference, pp. 53–62, IOS Press, Maastricht, the Netherlands, 2023.
• Discovering the Rationale of Decisions In: Schlobach, S.; Pérez-Ortiz, M.; Tielman, M. (Ed.): Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence, pp. 255–257, IOS Press, Amsterdam, the Netherlands, 2022.
• Arguments, rules and cases in law: Resources for aligning learning and reasoning in structured domains In: Argument & Computation, vol. 14, pp. 235–243, 2023, ISSN: 1946-2174, (2).
• Discovering the Rationale of Decisions: Towards a Method for Aligning Learning and Reasoning In: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law, pp. 235–239, Association for Computing Machinery, São Paulo, Brazil, 2021.
• Discovering the Rationale of Decisions: Experiments on Aligning Learning and Reasoning In: 4th EXplainable AI in Law Workshop (XAILA 2021), pp. 235–239, ACM, 2021.
• Rationale Discovery and Explainable AI In: Erich, Schweighofer (Ed.): Legal Knowledge and Information Systems – JURIX 2021: The Thirty-fourth Annual Conference, Vilnius, Lithuania, 8-10 December 2021, pp. 225–234, IOS Press, 2021.