Exploring Verification Frameworks for Social Choice Alignment

Jessica Ciupa, Vaishak Belle, Ekaterina Komendantskaya
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:439-446, 2025.

Abstract

The deployment of autonomous agents that interact with humans in safety-critical situations raises new research problems as we move towards fully autonomous systems in domains such as autonomous vehicles or search and rescue. If autonomous agents are placed in a dilemma, how would they act? The literature in computational ethics has explored the actions and learning methods that emerge in ethical dilemmas. However, our position paper examines how ethical dilemmas are not isolated in a social vacuum. Our central claim in our position paper is that to enable trust among all human users, a neuralsymbolic verification of moral preference alignment is required. We propose that the formal robustness properties be applied to social choice modelling. We outline how robustness properties can help validate the formation of stable social preference clusters in deep neural network classifiers. Our initial results highlight the vulnerabilities of models in moral-critical scenarios to perturbations, suggesting a verification-training loop for improved robustness. We position this work as an inquiry into the viability of verifying moral preference alignment, based on our initial results. Ultimately, we aim to contribute to the broader interdisciplinary effort that integrates formal methods, social choice theory, and empirical moral psychology for interpretable computational ethics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-ciupa25a, title = {Exploring Verification Frameworks for Social Choice Alignment}, author = {Ciupa, Jessica and Belle, Vaishak and Komendantskaya, Ekaterina}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {439--446}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/ciupa25a/ciupa25a.pdf}, url = {https://proceedings.mlr.press/v284/ciupa25a.html}, abstract = {The deployment of autonomous agents that interact with humans in safety-critical situations raises new research problems as we move towards fully autonomous systems in domains such as autonomous vehicles or search and rescue. If autonomous agents are placed in a dilemma, how would they act? The literature in computational ethics has explored the actions and learning methods that emerge in ethical dilemmas. However, our position paper examines how ethical dilemmas are not isolated in a social vacuum. Our central claim in our position paper is that to enable trust among all human users, a neuralsymbolic verification of moral preference alignment is required. We propose that the formal robustness properties be applied to social choice modelling. We outline how robustness properties can help validate the formation of stable social preference clusters in deep neural network classifiers. Our initial results highlight the vulnerabilities of models in moral-critical scenarios to perturbations, suggesting a verification-training loop for improved robustness. We position this work as an inquiry into the viability of verifying moral preference alignment, based on our initial results. Ultimately, we aim to contribute to the broader interdisciplinary effort that integrates formal methods, social choice theory, and empirical moral psychology for interpretable computational ethics.} }
Endnote
%0 Conference Paper %T Exploring Verification Frameworks for Social Choice Alignment %A Jessica Ciupa %A Vaishak Belle %A Ekaterina Komendantskaya %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-ciupa25a %I PMLR %P 439--446 %U https://proceedings.mlr.press/v284/ciupa25a.html %V 284 %X The deployment of autonomous agents that interact with humans in safety-critical situations raises new research problems as we move towards fully autonomous systems in domains such as autonomous vehicles or search and rescue. If autonomous agents are placed in a dilemma, how would they act? The literature in computational ethics has explored the actions and learning methods that emerge in ethical dilemmas. However, our position paper examines how ethical dilemmas are not isolated in a social vacuum. Our central claim in our position paper is that to enable trust among all human users, a neuralsymbolic verification of moral preference alignment is required. We propose that the formal robustness properties be applied to social choice modelling. We outline how robustness properties can help validate the formation of stable social preference clusters in deep neural network classifiers. Our initial results highlight the vulnerabilities of models in moral-critical scenarios to perturbations, suggesting a verification-training loop for improved robustness. We position this work as an inquiry into the viability of verifying moral preference alignment, based on our initial results. Ultimately, we aim to contribute to the broader interdisciplinary effort that integrates formal methods, social choice theory, and empirical moral psychology for interpretable computational ethics.
APA
Ciupa, J., Belle, V. & Komendantskaya, E.. (2025). Exploring Verification Frameworks for Social Choice Alignment. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:439-446 Available from https://proceedings.mlr.press/v284/ciupa25a.html.

Related Material