Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour

Authors: Andrea Aler Tubella, Andreas Theodorou, Frank Dignum, Virginia Dignum

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a Glass-Box around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. [...] In the penultimate section we provide an example of how our approach can be applied to a real-world intelligent system.
Researcher Affiliation Academia Andrea Aler Tubella , Andreas Theodorou , Frank Dignum and Virginia Dignum Ume a University {andrea.aler, andreas.theodorou, frank.dignum, virginia.dignum}@umu.se
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks. It describes the two stages of the Glass-Box approach conceptually, accompanied by a diagram (Figure 1).
Open Source Code No The paper does not provide concrete access to source code for the methodology described. It is a conceptual paper outlining an approach.
Open Datasets No The paper presents a conceptual approach and illustrates it with a use case (mortgage decisions) rather than conducting experiments on a dataset. Therefore, no information on public datasets for training is provided.
Dataset Splits No The paper does not describe experiments with data. Consequently, there are no training, validation, or test dataset splits mentioned.
Hardware Specification No The paper is conceptual and does not describe running experiments. Therefore, no specific hardware specifications are mentioned.
Software Dependencies No The paper does not describe running experiments or implementing software that would require specific dependencies with version numbers.
Experiment Setup No The paper describes a conceptual framework and a use case, but does not detail an experimental setup, hyperparameters, or system-level training settings.