Appendix A — Publications

Keywords

Artificial Intelligence, Trustworthy AI, Counterfactual Explanations, Algorithmic Recourse

The following is a list of publications falling into one of the following two categories:

  1. The publication is included as chapter in this thesis.
  2. The publication was released during Patrick’s Ph.D. trajectory and: (a) lists Patrick as a (co-)author; (b) is broadly related to this thesis.

All of the papers listed here have either already been published or they have been accepted for publication, unless otherwise stated below:

  • Buszydlik et al. (2024) received positive reviews at NeurIPS 2024, but ultimately ended up as a border-line ‘reject’ on the basis of not being going fit for the venue.

Academic Research

Patrick Altmeyer, Aleksander Buszydlik, Arie Deursen, Cynthia C. S. Liem (2026). ‘Counterfactual Training: Teaching Models Plausible and Actionable Explanations’. In 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). Available at: upcoming. (Chapter 5)

Aleksander Buszydlik, Patrick Altmeyer, Cynthia C. S. Liem, Roel Dobbe (2025). ‘Understanding the Affordances and Constraints of Explainable AI in Safety-Critical Contexts: A Case Study in Dutch Social Welfare’. In Electronic Government. EGOV 2025. Lecture Notes in Computer Science. Available at: https://link.springer.com/chapter/10.1007/978-3-032-02515-9_8

Karol Dobiczek, Patrick Altmeyer, Cynthia CS Liem (2025). ‘Natural Language Counterfactual Explanations in Financial Text Classification: A Comparison of Generators and Evaluation Metrics’. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM\(^2\)), 958–972. Available at: https://aclanthology.org/2025.gem-1.75.pdf

Aleksander Buszydlik, Patrick Altmeyer, Cynthia C. S. Liem, Roel Dobbe (2024). ‘Grounding and Validation of Algorithmic Recourse in Real-World Contexts: A Systematized Literature Review’. Available at: https://openreview.net/pdf?id=oEmyoy5H5P

Patrick Altmeyer, Mojtaba Farmanbar, Arie van Deursen, Cynthia C. S. Liem (2024). ‘Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals’. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 10829–10837, (38). DOI: https://doi.org/10.1609/aaai.v38i10.28956. (Chapter 4)

Patrick Altmeyer, Andrew M Demetriou, Antony Bartlett, Cynthia C. S. Liem (2024). ‘Position: Stop Making Unscientific AGI Performance Claims’. In International Conference on Machine Learning, 1222–1242. Available at: https://proceedings.mlr.press/v235/altmeyer24a.html. (Chapter 6)

Floris Hengst, Ralf Wolter, Patrick Altmeyer, Arda Kaygan (2024). ‘Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition’. In Findings of the Association for Computational Linguistics: NAACL 2024, 2412–2432. DOI: https://doi.org/10.18653/v1/2024.findings-naacl.156

Marc Agustí, Ignacio Vidal-Quadras Costa, Patrick Altmeyer (2023). ‘Deep vector autoregression for macroeconomic data’. In IFC Bulletins chapters, (59). Available at: https://www.bis.org/ifc/publ/ifcb59_39.pdf

Patrick Altmeyer, Giovan Angela, Aleksander Buszydlik, Karol Dobiczek, Arie van Deursen, Cynthia C. S. Liem (2023). ‘Endogenous Macrodynamics in Algorithmic Recourse’. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 418–431. DOI: https://doi.org/10.1109/satml54575.2023.00036. (Chapter 3)

Patrick Altmeyer, Arie van Deursen, Cynthia C. S. Liem (2023). ‘Explaining Black-Box Models through Counterfactuals’. In Proceedings of the JuliaCon Conferences, 130, (1). DOI: https://doi.org/10.21105/jcon.00130. (Chapter 2)

Research Software

Patrick Altmeyer, contributors (2025). ‘CounterfactualExplanations.jl’. DOI: https://doi.org/10.5281/zenodo.8239378

Patrick Altmeyer, contributors (2024). ‘ConformalPrediction.jl’. DOI: https://doi.org/10.5281/zenodo.12799930

Patrick Altmeyer, contributors (2024). ‘LaplaceRedux.jl’. DOI: https://doi.org/10.5281/zenodo.13758044