Research Papers

Answer Set Programming (ASP) is a powerful declarative programming paradigm commonly used for solving challenging search and optimization problems. The modeling languages of ASP are supported by sophisticated solving algorithms (solvers) that make the solution search efficient while enabling the programmer to model the problem at a high level of abstraction. As an approach to Knowledge Representation and Reasoning, ASP benefits from its simplicity, conciseness and rigorously defined semantics. These characteristics make ASP a straightforward way to develop formally verifiable programs. In the context of artificial intelligence (AI), the clarity of ASP programs lends itself to the construction of explainable, trustworthy AI. In support of these goals, my research is concerned with extending the theory and tools supporting the verification of ASP progams.

The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train fair models from scratch, how to automatically reveal and explain the unfairness of a trained model remains a challenging task. Revealing unfairness of machine learning models in interpretable fashion is a critical step towards fair and trustworthy AI. In this paper, we systematically tackle the novel task of revealing unfair models by mining interpretable evidence (RUMIE). The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model. To make the evidence interpretable, we also find a set of human-understandable key attributes and decision rules that characterize the discriminated data instances and distinguish them from the other non-discriminated data. As demonstrated by extensive experiments on many real-world data sets, our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models. Moreover, it is much more scalable than all of the baseline methods.

The recent spike in certified Artificial Intelligence (AI) tools for healthcare has renewed the debate around adoption of this technology. One thread of such debate concerns Explainable AI and its promise to render AI devices more transparent and trustworthy. A few voices active in the medical AI space have expressed concerns on the reliability of Explainable AI techniques, questioning their use and inclusion in guidelines and standards. Revisiting such criticisms, this article offers a balanced and comprehensive perspective on the utility of Explainable AI, focusing on the specificity of clinical applications of AI and placing them in the context of healthcare interventions. Against its detractors and despite valid concerns, we argue that the Explainable AI research program is still central to human-machine interaction and ultimately our main tool against loss of control, a danger that cannot be prevented by rigorous clinical validation alone.

Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models

Liu Zhendong, Wenyu Jiang, Yi Zhang +1

With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned. We explore the limitations of post-hoc explanation methods that use approximators to mimic the behavior of black-box models. Then we propose eXplanation-based Counterfactual Retraining (XCR), which extracts feature importance fastly. XCR applies the explanations generated by the XAI model as counterfactual input to retrain the black-box model to address OOD and social misalignment problems. Evaluation of popular image datasets shows that XCR can improve model performance when only retaining 12.5% of the most crucial features without changing the black-box model structure. Furthermore, the evaluation of the benchmark of corruption datasets shows that the XCR is very helpful for improving model robustness and positively impacts the calibration of OOD problems. Even though not calibrated in the validation set like some OOD calibration methods, the corrupted data metric outperforms existing methods. Our method also beats current OOD calibration methods on the OOD calibration metric if calibration on the validation set is applied.

Linear Programs (LPs) have been one of the building blocks in machine learning and have championed recent strides in differentiable optimizers for learning systems. While there exist solvers for even high-dimensional LPs, understanding said high-dimensional solutions poses an orthogonal and unresolved problem. We introduce an approach where we consider neural encodings for LPs that justify the application of attribution methods from explainable artificial intelligence (XAI) designed for neural learning systems. The several encoding functions we propose take into account aspects such as feasibility of the decision space, the cost attached to each input, or the distance to special points of interest. We investigate the mathematical consequences of several XAI methods on said neural LP encodings. We empirically show that the attribution methods Saliency and LIME reveal indistinguishable results up to perturbation levels, and we propose the property of Directedness as the main discriminative criterion between Saliency and LIME on one hand, and a perturbation-based Feature Permutation approach on the other hand. Directedness indicates whether an attribution method gives feature attributions with respect to an increase of that feature. We further notice the baseline selection problem beyond the classical computer vision setting for Integrated Gradients.

Do We Need Another Explainable AI Method? Toward Unifying Post-hoc XAI Evaluation Methods into an Interactive and Multi-dimensional Benchmark

Mohamed Karim Belaid, Eyke Hüllermeier, Maximilian Rabus +1

In recent years, Explainable AI (xAI) attracted a lot of attention as various countries turned explanations into a legal right. xAI allows for improving models beyond the accuracy metric by, e.g., debugging the learned pattern and demystifying the AI's behavior. The widespread use of xAI brought new challenges. On the one hand, the number of published xAI algorithms underwent a boom, and it became difficult for practitioners to select the right tool. On the other hand, some experiments did highlight how easy data scientists could misuse xAI algorithms and misinterpret their results. To tackle the issue of comparing and correctly using feature importance xAI algorithms, we propose Compare-xAI, a benchmark that unifies all exclusive functional testing methods applied to xAI algorithms. We propose a selection protocol to shortlist non-redundant functional tests from the literature, i.e., each targeting a specific end-user requirement in explaining a model. The benchmark encapsulates the complexity of evaluating xAI methods into a hierarchical scoring of three levels, namely, targeting three end-user groups: researchers, practitioners, and laymen in xAI. The most detailed level provides one score per test. The second level regroups tests into five categories (fidelity, fragility, stability, simplicity, and stress tests). The last level is the aggregated comprehensibility score, which encapsulates the ease of correctly interpreting the algorithm's output in one easy to compare value. Compare-xAI's interactive user interface helps mitigate errors in interpreting xAI results by quickly listing the recommended xAI solutions for each ML task and their current limitations. The benchmark is made available at https://karim-53.github.io/cxai/

We describe an extension of the Fanoos XAI system [Bayani et al 2022] which enables the system to learn the appropriate action to take in order to satisfy a user's request for description to be made more or less abstract. Specifically, descriptions of systems under analysis are stored in states, and in order to make a description more or less abstract, Fanoos selects an operator from a large library to apply to the state and generate a new description. Prior work on Fanoos predominately used hand-written methods for operator-selection; this current work allows Fanoos to leverage experience to learn the best operator to apply in a particular situation, balancing exploration and exploitation, leveraging expert insights when available, and utilizing similarity between the current state and past states. Additionally, in order to bootstrap the learning process (i.e., like in curriculum learning), we describe a simulated user which we implemented; this simulation allows Fanoos to gain general insights that enable reasonable courses of action, insights which later can be refined by experience with real users, as opposed to interacting with humans completely from scratch. Code implementing the methods described in the paper can be found at https://github/DBay-ani/Operator_Selection_Learning_Extensions_For_Fanoos.

Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods rely on technical explanations that are difficult for clinicians and patients to interpret. We introduce Visualized Learning for Machine Learning (VL4ML), a human-centered explainability framework that communicates model predictions and uncertainty through intuitive visual representations rather than numerical or post-hoc explanations. By encoding diagnostic information in colors, patterns, and spatial structures, VL4ML enables users to interpret predictions without requiring knowledge of model internals or statistical expertise. We demonstrate the framework across multiple clinical tasks, including classification, regression, longitudinal prediction, and multimodal analysis. Its effectiveness was evaluated through a human-centered study involving 158 participants (39.2% clinical professionals) and an expert interpretability assessment. More than 79% of participants positively rated the visual explanations across evaluation dimensions, 84.0% found them more memorable than numeric outputs, and 76.9% reported faster decision-making. Over 82% successfully perceived uncertainty embedded in the visual representations without prior statistical training. No significant differences were observed between clinicians and non-clinicians or between male and female participants, indicating broad accessibility. These results suggest that VL4ML complements existing XAI and uncertainty quantification methods by providing intuitive, universally interpretable visual explanations that support transparent and trustworthy clinical decision-making.

The trustworthiness of neural networks is often challenged because they lack the ability to express uncertainty and explain their skill. This can be problematic given the increasing use of neural networks in high stakes decision-making such as in climate change applications. We address both issues by successfully implementing a Bayesian Neural Network (BNN), where parameters are distributions rather than deterministic, and applying novel implementations of explainable AI (XAI) techniques. The uncertainty analysis from the BNN provides a comprehensive overview of the prediction more suited to practitioners' needs than predictions from a classical neural network. Using a BNN means we can calculate the entropy (i.e. uncertainty) of the predictions and determine if the probability of an outcome is statistically significant. To enhance trustworthiness, we also spatially apply the two XAI techniques of Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanation (SHAP) values. These XAI methods reveal the extent to which the BNN is suitable and/or trustworthy. Using two techniques gives a more holistic view of BNN skill and its uncertainty, as LRP considers neural network parameters, whereas SHAP considers changes to outputs. We verify these techniques using comparison with intuition from physical theory. The differences in explanation identify potential areas where new physical theory guided studies are needed.

Teaching logic effectively requires an understanding of the factors which cause logic students to struggle. Formalization exercises, which require the student to produce a formula corresponding to the natural language sentence, are a good candidate for scrutiny since they tap into the students' understanding of various aspects of logic. We correlate the difficulty of formalization exercises predicted by a previously proposed difficulty estimation algorithm with two empirical difficulty measures on the Grade Grinder corpus, which contains student solutions to FOL exercises. We obtain a moderate correlation with both measures, suggesting that the said algorithm indeed taps into important sources of difficulty but leaves a fair amount of variance uncaptured. We conduct an error analysis, closely examining exercises which were misclassified, with the aim of identifying additional sources of difficulty. We identify three additional factors which emerge from the difficulty analysis, namely predicate complexity, pragmatic factors and typicality of the exercises, and discuss the implications of automated difficulty estimation for logic teaching and explainable AI.

The COVID-19 pandemic has caused millions of cases and deaths and the AI-related scientific community, after being involved with detecting COVID-19 signs in medical images, has been now directing the efforts towards the development of methods that can predict the progression of the disease. This task is multimodal by its very nature and, recently, baseline results achieved on the publicly available AIforCOVID dataset have shown that chest X-ray scans and clinical information are useful to identify patients at risk of severe outcomes. While deep learning has shown superior performance in several medical fields, in most of the cases it considers unimodal data only. In this respect, when, which and how to fuse the different modalities is an open challenge in multimodal deep learning. To cope with these three questions here we present a novel approach optimizing the setup of a multimodal end-to-end model. It exploits Pareto multi-objective optimization working with a performance metric and the diversity score of multiple candidate unimodal neural networks to be fused. We test our method on the AIforCOVID dataset, attaining state-of-the-art results, not only outperforming the baseline performance but also being robust to external validation. Moreover, exploiting XAI algorithms we figure out a hierarchy among the modalities and we extract the features' intra-modality importance, enriching the trust on the predictions made by the model.

The right to AI explainability has consolidated as a consensus in the research community and policy-making. However, a key component of explainability has been missing: extrapolation, which describes the extent to which AI models can be clueless when they encounter unfamiliar samples (i.e., samples outside the convex hull of their training sets, as we will explain). We report that AI models extrapolate outside their range of familiar data, frequently and without notifying the users and stakeholders. Knowing whether a model has extrapolated or not is a fundamental insight that should be included in explaining AI models in favor of transparency and accountability. Instead of dwelling on the negatives, we offer ways to clear the roadblocks in promoting AI transparency. Our analysis commentary accompanying practical clauses useful to include in AI regulations such as the National AI Initiative Act in the US and the AI Act by the European Commission.