With the widespread use of artificial intelligence, it becomes crucial to provide information about these systems and how they are used. Governments aim to disclose their use of algorithms to establish legitimacy and the EU AI Act mandates forms of transparency for all high-risk and limited-risk systems. Yet, what should the standards for transparency be? What information is needed to show to a wide public that a certain system can be used legitimately and responsibly? I argue that process-based approaches fail to satisfy, as knowledge about the development process is insufficient to predict the properties of the resulting system. Current outcome-based approaches [Mitchell et al., 2019; Loi et al., 2021] are also criticized for a lack of attention to the broader socio-technical system and failure to account for empirical results that show that people care about more than just the outcomes of a process [as reported by Meyerson et al. (Procedural justice and relational theory: Empirical, philosophical, and legal perspectives, Taylor & Francis, 2021)]. Instead, I propose value-based transparency, on which the information we need to provide is what values have been considered in the design and how successful these have been realized in the final system. This can handle the objections to other frameworks, matches with current best practices on the design of responsible AI and provides the public with information on the crucial aspects of a system’s design.@en

AI is becoming significantly more impactful in society, especially with regard to decision-making. Algorithmic fairness is the field wherein the fairness of an AI algorithm is defined, subsequently evaluated, and ideally improved. This paper uses a fairness decision tree to critique certain notions of algorithmic fairness through a postcolonial lens by applying Gayatri Spivak's theory of the subaltern alongside other postcolonial principles. A definition and criteria for a subaltern population in AI are provided, depicting that AI and algorithmic fairness rely on subaltern marginalization, silence, and faux inclusion. A theoretical case analysis is then conducted to illustrate how demographic parity, even in cases where it is the best fairness metric, does not include the subaltern. Algorithmic fairness often defines fairness through neoliberalism, assigning a ``cost'' to ethical considerations, wherein morality is second to profits and utility. Furthermore, a large proportion of the ``justice'' conducted through AI is surface level and may actually cause more harm in the long run. A proposal is made to seriously consider not using any AI in socially relevant, complex situations.

This research investigates how biases in datasets influence the outputs of decision-making algorithms, specifically whether these biases are merely reflected or further amplified by the algorithms. Using the Adult/Census Income dataset from the UCI Machine Learning Repository, the research explores biases through the lens of three machine learning models: Logistic Regression, Decision Tree, and Random Forest. The analysis reveals that all models exhibit varying degrees of bias, dependent on the fairness metrics applied: Demographic Parity, Disparate Impact, Equal Opportunity, Equalized Odds. It has been found that higher accuracy does not necessarily equate to fairness. The findings emphasize the complex nature of algorithmic bias and the challenge of achieving fairness in automated decision-making systems. This research contributes to the understanding of bias amplification in algorithms and underscores the need for continued efforts to develop fairer decision-making systems in various sectors.

Algorithmic bias due to training from biased data is a widespread issue. Bias mitigation techniques such as fairness-oriented data pre-, in-, and post-processing can help but usually come at the cost of model accuracy. For this contribution, we first conducted a literature review to get a better insight into the potential trade-offs. We followed by implementing a Python program to test how the Disparate Impact Remover (DIR) pre-processing and Reject Option Classification (ROC) post-processing techniques impacted the fairness and accuracy metric values of a Logistic Regression model trained on data from the Adult Income dataset. The implementation also allows for building Pareto fronts that trade off fairness and accuracy metrics of choice, thus offering a blend of perspectives on fairness. Our findings give insight into how combined fairness methods influence the trade-off, but our implementation can be extended to explore such trade-offs using other datasets, models, and fairness methods.

Algorithms have a more prominent presence than ever in the domain of recruitment. Many different tasks ranging from finding candidates to scanning resumes are handled more and more by algorithms and less by humans. Automating these tasks has led to bias being exhibited towards different unprivileged groups, among these women. This has prompted a need to find solutions to this bias in order to achieve fairness in algorithms for everyone. This survey analyses the state of the literature on fairness and bias against women with a focus on recruitment algorithms. It has been found that a plethora of methods to achieve and measure fairness exist, with many of the technical methods having only been tested in a controlled environment and not in a production environment. Companies are not very forthcoming in sharing how they ensure fairness, which complicates the development of the field. There are many limitations to the current methods, however due to widespread usage of algorithms in the recruitment process, there is still a need for solutions to exist while these critiques are being addressed. It is vital for fairness to not only consider technical solutions, but also social solutions and to be aware of the limitations of each approach. Solving the issue of bias against women in algorithms requires sometimes realising that the best solution does not involve an algorithm at all, or in the case where an algorithm is applied, a critical engineer that is aware of the limitations and possibilities of different methods to achieve fairness. Future work is in addressing some major critiques of the current fairness literature and reducing the bias in society that often leads to algorithmic bias.

Machine learning is used more and more in scientific contexts, from the recent breakthroughs with AlphaFold2 in protein fold prediction to the use of ML in parametrization for large climate/astronomy models. Yet it is unclear whether we can obtain scientific explanations from such models. I argue that when machine learning is used to conduct causal inference we can give a new positive answer to this question. However, these ML models are purpose-built models and there are technical results showing that standard machine learning models cannot be used for the same type of causal inference. Instead, there is a pathway to causal explanations from predictive ML models through new explainability techniques; specifically, new methods to extract structural equation models from such ML models. The extracted models are likely to suffer from issues though: they will often fail to account for confounders and colliders, as well as deliver simply incorrect causal graphs due to ML models tendency to violate physical laws such as the conservation of energy. In this case, extracted graphs are a starting point for new explanations, but predictive accuracy is no guarantee for good explanations.

@en

AI systems are increasingly being used to support human decision making. It is important that AI advice is followed appropriately. However, according to existing literature, users typically under-rely or over-rely on AI systems, and this leads to sub-optimal team performance. In this context, we investigate the role of stated system accuracy by contrasting the lack of system information with the presence of system accuracy in a loan prediction task. We explore how the degree to which humans understand system accuracy influences their reliance on the AI system, by investigating numeracy levels and with the aid of analogies to explain system accuracy in a first of its kind between-subjects study (N=281). We found that explaining the stated accuracy of a system using analogies failed to help users rely on the AI systemappropriately (i.e., the tendency of users to rely on the system when the system is correct, or on themselves otherwise). To eliminate the impact of subjective attitudes towards analogy domains, we conducted a within-subjects study (N=248) where each participant worked on tasks with analogy-based explanations from different domains. Results from this second study confirmed that explaining stated accuracy of the system with analogies was not sufficient to facilitate appropriate reliance on the AI system in the context of loan prediction tasks, irrespective of individual user differences. Based on our findings from the two studies, we reason that the under-reliance on the AI system may be a result of users' overestimation of their own ability to solve the given task. Thus, although familiar analogies can be effective in improving the intelligibility of stated accuracy of the system, an improved understanding of system accuracy does not necessarily lead to improved system reliance and team performance.

@en

Users of sociotechnical systems often have no way to independently verify whether the system output which they use to make decisions is correct; they are epistemically dependent on the system. We argue that this leads to problems when the system is wrong, namely to bad decisions and violations of the norm of practical reasoning. To prevent this from occurring we suggest the implementation of defeaters: information that a system is unreliable in a specific case (undercutting defeat) or independent information that the output is wrong (rebutting defeat). Practically, we suggest to design defeaters based on the different ways in which a system might produce erroneous outputs, and analyse this suggestion with a case study of the risk classification algorithm used by the Dutch tax agency.@en

With recent advances in explainable artificial intelligence (XAI), researchers have started to pay attention to concept-level explanations, which explain model predictions with a high level of abstraction. However, such explanations may be difficult to digest for laypeople due to the potential knowledge gap and the concomitant cognitive load. Inspired by recent work, we argue that analogy-based explanations composed of commonsense knowledge may be a potential solution to tackle this issue. In this paper, we propose analogical inference as a bridge to help end-users leverage their commonsense knowledge to better understand the concept-level explanations. Specifically, we design an effective analogy-based explanation generation method and collect 600 analogy-based explanations from 100 crowd workers. Furthermore, we propose a set of structured dimensions for the qualitative assessment of analogy-based explanations and conduct an empirical evaluation of the generated analogies with experts. Our findings reveal significant positive correlations between the qualitative dimensions of analogies and the perceived helpfulness of analogy-based explanations. These insights can inform the design of future methods for the generation of effective analogy-based explanations. We also find that the understanding of commonsense explanations varies with the experience of the recipient user, which points out the need for further work on personalization when leveraging commonsense explanations. @en

Explaining the behaviour of Artificial Intelligence models has become a necessity. Their opaqueness and fragility are not tolerable in high-stakes domains especially. Although considerable progress is being made in the field of Explainable Artificial Intelligence, scholars have demonstrated limits and flaws of existing approaches: explanations requiring further interpretation, non-standardised explanatory format, and overall fragility. In light of this fragmentation, we turn to the field of philosophy of science to understand what constitutes a good explanation, that is, a generalisation that covers both the actual outcome and, possibly multiple, counterfactual outcomes. Inspired by this, we propose CHIME: a human-in-the-loop, post-hoc approach focused on creating such explanations by establishing the causal features in the input. We first elicit people's cognitive abilities to understand what parts of the input the model might be attending to. Then, through Causal Discovery we uncover the underlying causal graph relating the different concepts. Finally, with such a structure, we compute the causal effects different concepts have towards a model's outcome. We evaluate the Fidelity, Coherence, and Accuracy of the explanations obtained with CHIME with respect to two state-of-the-art Computer Vision models trained on real-world image data sets. We found evidence that the explanations reflect the causal concepts tied to a model's prediction, both in terms of causal strength and accuracy.@en

Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI.@en

In recent years philosophers have used results from cognitive science to formulate epistemologies of arithmetic (e.g. Giaquinto in J Philos 98(1):5–18, 2001). Such epistemologies have, however, been criticised, e.g. by Azzouni (Talking about nothing: numbers, hallucinations and fictions, Oxford University Press, 2010), for interpreting the capacities found by cognitive science in an overly numerical way. I offer an alternative framework for the way these psychological processes can be combined, forming the basis for an epistemology for arithmetic. The resulting framework avoids assigning numerical content to the Approximate Number System and Object Tracking System, two systems that have so far been the basis of epistemologies of arithmetic informed by cognitive science. The resulting account is, however, only a framework for an epistemology: in the final part of the paper I argue that it is compatible with both platonist and nominalist views of numbers by fitting it into an epistemology for ante rem structuralism and one for fictionalism. Unsurprisingly, cognitive science does not settle the debate between these positions in the philosophy of mathematics, but I it can be used to refine existing epistemologies and restrict our focus to the capacities that cognitive science has found to underly our mathematical knowledge.@en