Robust XAI techniques should ideally be simultaneously deterministic, model agnostic, and guaranteed to converge. We propose MULTIDIMENSIONAL PROBLEM AGNOSTIC EXPLAINABLE AI (MUPAX), a deterministic, model agnostic explainability technique, with guaranteed convergency. MUPAX measure theoretic formulation gives principled feature importance attribution through structured perturbation analysis that discovers inherent input patterns and eliminates spurious relationships. We evaluate MUPAX on an extensive range of data modalities and tasks: audio classification (1D), image classification (2D), volumetric medical image analysis (3D), and anatomical landmark detection, demonstrating dimension agnostic effectiveness. The rigorous convergence guarantees extend to any loss function and arbitrary dimensions, making MUPAX applicable to virtually any problem context for AI. By contrast with other XAI methods that typically decrease performance when masking, MUPAX not only preserves but actually enhances model accuracy by capturing only the most important patterns of the original data. Extensive benchmarking against the state of the XAI art demonstrates MUPAX ability to generate precise, consistent and understandable explanations, a crucial step towards explainable and trustworthy AI systems. The source code will be released upon publication.
Understanding and predicting the activity of oxide perovskite catalysts for the oxygen evolution reaction (OER) requires descriptors that are both accurate and physically interpretable. While symbolic regression (SR) offers a path to discover such formulas, its performance degrades with high-dimensional inputs and small datasets. We present a two-phase framework that combines neural networks (NN), feature importance analysis, and symbolic regression (SR) to discover interpretable descriptors for OER activity in oxide perovskites. In Phase I, using a small dataset and seven structural features, we reproduce and improve the known {\mu}/t descriptor by engineering composite features and applying symbolic regression, achieving training and validation MAEs of 22.8 and 20.8 meV, respectively. In Phase II, we expand to 164 features, reduce dimensionality, and identify LUMO energy as a key electronic descriptor. A final formula using {\mu}/t, {\mu}/RA, and LUMO energy achieves improved accuracy (training and validation MAEs of 22.1 and 20.6 meV) with strong physical interpretability. Our results demonstrate that NN-guided symbolic regression enables accurate, interpretable, and physically meaningful descriptor discovery in data-scarce regimes, indicating interpretability need not sacrifice accuracy for materials informatics.
School dropout is a serious problem in distance learning, where early detection is crucial for effective intervention and student perseverance. Predicting student dropout using available educational data is a widely researched topic in learning analytics. Our partner's distance learning platform highlights the importance of integrating diverse data sources, including socio-demographic data, behavioral data, and sentiment analysis, to accurately predict dropout risks. In this paper, we introduce a novel model that combines sentiment analysis of student comments using the Bidirectional Encoder Representations from Transformers (BERT) model with socio-demographic and behavioral data analyzed through Extreme Gradient Boosting (XGBoost). We fine-tuned BERT on student comments to capture nuanced sentiments, which were then merged with key features selected using feature importance techniques in XGBoost. Our model was tested on unseen data from the next academic year, achieving an accuracy of 84\%, compared to 82\% for the baseline model. Additionally, the model demonstrated superior performance in other metrics, such as precision and F1-score. The proposed method could be a vital tool in developing personalized strategies to reduce dropout rates and encourage student perseverance
Explainable AI (XAI) methods often struggle to generate clear, interpretable outputs for users without domain expertise. We introduce Feature-Guided Neighbor Selection (FGNS), a post hoc method that enhances interpretability by selecting class-representative examples using both local and global feature importance. In a user study (N = 98) evaluating Kannada script classifications, FGNS significantly improved non-experts' ability to identify model errors while maintaining appropriate agreement with correct predictions. Participants made faster and more accurate decisions compared to those given traditional k-NN explanations. Quantitative analysis shows that FGNS selects neighbors that better reflect class characteristics rather than merely minimizing feature-space distance, leading to more consistent selection and tighter clustering around class prototypes. These results support FGNS as a step toward more human-aligned model assessment, although further work is needed to address the gap between explanation quality and perceived trust.
Pathology image segmentation is crucial in computational pathology for analyzing histological features relevant to cancer diagnosis and prognosis. However, current methods face major challenges in clinical applications due to limited annotated data and restricted category definitions. To address these limitations, we propose PathSegmentor, the first text-prompted segmentation foundation model designed specifically for pathology images. We also introduce PathSeg , the largest and most comprehensive dataset for pathology segmentation, built from 17 public sources and containing 275k image-mask-label triples across 160 diverse categories. With PathSegmentor, users can perform semantic segmentation using natural language prompts, eliminating the need for laborious spatial inputs such as points or boxes. Extensive experiments demonstrate that PathSegmentor outperforms specialized models with higher accuracy and broader applicability, while maintaining a compact architecture. It significantly surpasses existing spatial- and text-prompted models by 0.145 and 0.429 in overall Dice scores, respectively, showing strong robustness in segmenting complex structures and generalizing to external datasets. Moreover, PathSegmentor's outputs enhance the interpretability of diagnostic models through feature importance estimation and imaging biomarker discovery, offering pathologists evidence-based support for clinical decision-making. This work advances the development of explainable AI in precision oncology.
Predictive Process Monitoring (PPM) often uses deep learning models to predict the future behavior of ongoing processes, such as predicting process outcomes. While these models achieve high accuracy, their lack of interpretability undermines user trust and adoption. Explainable AI (XAI) aims to address this challenge by providing the reasoning behind the predictions. However, current evaluations of XAI in PPM focus primarily on functional metrics (such as fidelity), overlooking user-centered aspects such as their effect on task performance and decision-making. This study investigates the effects of explanation styles (feature importance, rule-based, and counterfactual) and perceived AI accuracy (low or high) on decision-making in PPM. We conducted a decision-making experiment, where users were presented with the AI predictions, perceived accuracy levels, and explanations of different styles. Users' decisions were measured both before and after receiving explanations, allowing the assessment of objective metrics (Task Performance and Agreement) and subjective metrics (Decision Confidence). Our findings show that perceived accuracy and explanation style have a significant effect.
In domains where transparency and trustworthiness are crucial, such as healthcare, rule-based systems are widely used and often preferred over black-box models for decision support systems due to their inherent interpretability. However, as rule-based models grow complex, discerning crucial features, understanding their interactions, and comparing feature contributions across different rule sets becomes challenging. To address this, we propose a comprehensive framework for estimating feature contributions in rule-based systems, introducing a graph-based feature visualisation strategy, a novel feature importance metric agnostic to rule-based predictors, and a distance metric for comparing rule sets based on feature contributions. By experimenting on two clinical datasets and four rule-based methods (decision trees, logic learning machines, association rules, and neural networks with rule extraction), we showcase our method's capability to uncover novel insights on the combined predictive value of clinical features, both at the dataset and class-specific levels. These insights can aid in identifying new risk factors, signature genes, and potential biomarkers, and determining the subset of patient information that should be prioritised to enhance diagnostic accuracy. Comparative analysis of the proposed feature importance score with state-of-the-art methods on 15 public benchmarks demonstrates competitive performance and superior robustness. The method implementation is available on GitHub: https://github.com/ChristelSirocchi/rule-graph.
Electric Vehicles (EVs) are rapidly gaining adoption as a sustainable alternative to fuel-powered vehicles, making secure charging infrastructure essential. Despite traditional authentication protocols, recent results showed that attackers may steal energy through tailored relay attacks. One countermeasure is leveraging the EV's fingerprint on the current exchanged during charging. However, existing methods focus on the final charging stage, allowing malicious actors to consume substantial energy before being detected and repudiated. This underscores the need for earlier and more effective authentication methods to prevent unauthorized charging. Meanwhile, profiling raises privacy concerns, as uniquely identifying EVs through charging patterns could enable user tracking. In this paper, we propose a framework for uniquely identifying EVs using physical measurements from the early charging stages. We hypothesize that voltage behavior early in the process exhibits similar characteristics to current behavior in later stages. By extracting features from early voltage measurements, we demonstrate the feasibility of EV profiling. Our approach improves existing methods by enabling faster and more reliable vehicle identification. We test our solution on a dataset of 7408 usable charges from 49 EVs, achieving up to 0.86 accuracy. Feature importance analysis shows that near-optimal performance is possible with just 10 key features, improving efficiency alongside our lightweight models. This research lays the foundation for a novel authentication factor while exposing potential privacy risks from unauthorized access to charging data.
Understanding the distinction between causation and correlation is critical in Alzheimer's disease (AD) research, as it impacts diagnosis, treatment, and the identification of true disease drivers. This experiment investigates the relationships among clinical, cognitive, genetic, and biomarker features using a combination of correlation analysis, machine learning classification, and model interpretability techniques. Employing the XGBoost algorithm, we identified key features influencing AD classification, including cognitive scores and genetic risk factors. Correlation matrices revealed clusters of interrelated variables, while SHAP (SHapley Additive exPlanations) values provided detailed insights into feature contributions across disease stages. Our results highlight that strong correlations do not necessarily imply causation, emphasizing the need for careful interpretation of associative data. By integrating feature importance and interpretability with classical statistical analysis, this work lays groundwork for future causal inference studies aimed at uncovering true pathological mechanisms. Ultimately, distinguishing causal factors from correlated markers can lead to improved early diagnosis and targeted interventions for Alzheimer's disease.
Large language models (LLMs) seem to offer an easy path to interpretability: just ask them to explain their decisions. Yet, studies show that these post-hoc explanations often misrepresent the true decision process, as revealed by mismatches in feature importance. Despite growing evidence of this inconsistency, no systematic solutions have emerged, partly due to the high cost of estimating feature importance, which limits evaluations to small datasets. To address this, we introduce the Post-hoc Self-Consistency Bank (PSCB) - a large-scale benchmark of decisions spanning diverse tasks and models, each paired with LLM-generated explanations and corresponding feature importance scores. Analysis of PSCB reveals that self-consistency scores barely differ between correct and incorrect predictions. We also show that the standard metric fails to meaningfully distinguish between explanations. To overcome this limitation, we propose an alternative metric that more effectively captures variation in explanation quality. We use it to fine-tune LLMs via Direct Preference Optimization (DPO), leading to significantly better alignment between explanations and decision-relevant features, even under domain shift. Our findings point to a scalable path toward more trustworthy, self-consistent LLMs.
Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and computational efficiency. These advantages have led to their widespread deployment in high-stakes domains, where interpretability is essential for ensuring trustworthy predictions. This has motivated the development of popular local (i.e. sample-specific) feature importance (LFI) methods such as LIME and TreeSHAP. However, these approaches rely on approximations that ignore the model's internal structure and instead depend on potentially unstable perturbations. These issues are addressed in the global setting by MDI+, a feature importance method which exploits an equivalence between decision trees and linear models on a transformed node basis. However, the global MDI+ scores are not able to explain predictions when faced with heterogeneous individual characteristics. To address this gap, we propose Local MDI+ (LMDI+), a novel extension of the MDI+ framework to the sample specific setting. LMDI+ outperforms existing baselines LIME and TreeSHAP in identifying instance-specific signal features, averaging a 10% improvement in downstream task performance across twelve real-world benchmark datasets. It further demonstrates greater stability by consistently producing similar instance-level feature importance rankings across multiple random forest fits. Finally, LMDI+ enables local interpretability use cases, including the identification of closer counterfactuals and the discovery of homogeneous subgroups.
Code review is a key practice in software engineering, ensuring quality and collaboration. However, industrial Merge Request (MR) workflows often deviate from standardized review processes, with many MRs serving non-review purposes (e.g., drafts, rebases, or dependency updates). We term these cases deviations and hypothesize that ignoring them biases analytics and undermines ML models for review analysis. We identify seven deviation categories, occurring in 37.02% of MRs, and propose a few-shot learning detection method (91% accuracy). By excluding deviations, ML models predicting review completion time improve performance in 53.33% of cases (up to 2.25x) and exhibit significant shifts in feature importance (47% overall, 60% top-*k*). Our contributions include: (1) a taxonomy of MR deviations, (2) an AI-driven detection approach, and (3) empirical evidence of their impact on ML-based review analytics. This work aids practitioners in optimizing review efforts and ensuring reliable insights.
Caco-2 permeability serves as a critical in vitro indicator for predicting the oral absorption of drug candidates during early-stage drug discovery. To enhance the accuracy and efficiency of computational predictions, we systematically investigated the impact of eight molecular feature representation types including 2D/3D descriptors, structural fingerprints, and deep learning-based embeddings combined with automated machine learning techniques to predict Caco-2 permeability. Using two datasets of differing scale and diversity (TDC benchmark and curated OCHEM data), we assessed model performance across representations and identified PaDEL, Mordred, and RDKit descriptors as particularly effective for Caco-2 prediction. Notably, the AutoML-based model CaliciBoost achieved the best MAE performance. Furthermore, for both PaDEL and Mordred representations, the incorporation of 3D descriptors resulted in a 15.73% reduction in MAE compared to using 2D features alone, as confirmed by feature importance analysis. These findings highlight the effectiveness of AutoML approaches in ADMET modeling and offer practical guidance for feature selection in data-limited prediction tasks.
Recent studies comparing AI-generated and human-authored literary texts have produced conflicting results: some suggest AI already surpasses human quality, while others argue it still falls short. We start from the hypothesis that such divergences can be largely explained by genuine differences in how readers interpret and value literature, rather than by an intrinsic quality of the texts evaluated. Using five public datasets (1,471 stories, 101 annotators including critics, students, and lay readers), we (i) extract 17 reference-less textual features (e.g., coherence, emotional variance, average sentence length...); (ii) model individual reader preferences, deriving feature importance vectors that reflect their textual priorities; and (iii) analyze these vectors in a shared "preference space". Reader vectors cluster into two profiles: 'surface-focused readers' (mainly non-experts), who prioritize readability and textual richness; and 'holistic readers' (mainly experts), who value thematic development, rhetorical variety, and sentiment dynamics. Our results quantitatively explain how measurements of literary quality are a function of how text features align with each reader's preferences. These findings advocate for reader-sensitive evaluation frameworks in the field of creative text generation.
Road safety management teams utilize on historical accident logs to identify blackspots, which are inherently rare and sparse in space and time. Near-miss events captured through vehicle telematics and transmitted in real-time by connected vehicles reveal a unique potential of prevention due to their high frequency nature and driving engagement on the road. There is currently a lack of understanding of the high potential of near-miss data in real-time to proactively detect potential risky driving areas, in advance of a fatal collision. This paper aims to spatially identify clusters of reported accidents (A) versus high-severity near-misses (High-G) within an urban environment (Sydney, Australia) and showcase how the presence of near-misses can significantly lead to future crashes in identified risky hotspots. First, by utilizing a 400m grid framework, we identify significant crash hotspots using the Getis-Ord $G_i^*$ statistical approach. Second, we employ a Bivariate Local Moran's I (LISA) approach to assess and map the spatial concordance and discordance between official crash counts (A) and High-G counts from nearmiss data (High-G). Third, we classify areas based on their joint spatial patterns into: a) High-High (HH) as the most riskiest areas in both historical logs and nearmiss events, High-Low (HL) for high crash logs but low nearmiss records, c) Low-High (LH) for low past crash records but high nearmiss events, and d) Low-Low (LL) for safe areas. Finally, we run a feature importance ranking on all area patterns by using a contextual Point of Interest (POI) count features and we showcase which factors are the most critical to the occurrence of crash blackspots.
The importance of clinical variables in the prognosis of the disease is explained using statistical correlation or machine learning (ML). However, the predictive importance of these variables may not represent their causal relationships with diseases. This paper uses clinical variables from a heart failure (HF) patient cohort to investigate the causal explainability of important variables obtained in statistical and ML contexts. Due to inherent regression modeling, popular causal discovery methods strictly assume that the cause and effect variables are numerical and continuous. This paper proposes a new computational framework to enable causal structure discovery (CSD) and score the causal strength of mixed-type (categorical, numerical, binary) clinical variables for binary disease outcomes. In HF classification, we investigate the association between the importance rank order of three feature types: correlated features, features important for ML predictions, and causal features. Our results demonstrate that CSD modeling for nonlinear causal relationships is more meaningful than its linear counterparts. Feature importance obtained from nonlinear classifiers (e.g., gradient-boosting trees) strongly correlates with the causal strength of variables without differentiating cause and effect variables. Correlated variables can be causal for HF, but they are rarely identified as effect variables. These results can be used to add the causal explanation of variables important for ML-based prediction modeling.
Explainability is crucial for improving the transparency of black-box machine learning models. With the advancement of explanation methods such as LIME and SHAP, various XAI performance metrics have been developed to evaluate the quality of explanations. However, different explainers can provide contrasting explanations for the same prediction, introducing trade-offs across conflicting quality metrics. Although available aggregation approaches improve robustness, reducing explanations' variability, very limited research employed a multi-criteria decision-making approach. To address this gap, this paper introduces a multi-criteria rank-based weighted aggregation method that balances multiple quality metrics simultaneously to produce an ensemble of explanation models. Furthermore, we propose rank-based versions of existing XAI metrics (complexity, faithfulness and stability) to better evaluate ranked feature importance explanations. Extensive experiments on publicly available datasets demonstrate the robustness of the proposed model across these metrics. Comparative analyses of various multi-criteria decision-making and rank aggregation algorithms showed that TOPSIS and WSUM are the best candidates for this use case.
The transition from traditional power grids to smart grids, significant increase in the use of renewable energy sources, and soaring electricity prices has triggered a digital transformation of the energy infrastructure that enables new, data driven, applications often supported by machine learning models. However, the majority of the developed machine learning models rely on univariate data. To date, a structured study considering the role meta-data and additional measurements resulting in multivariate data is missing. In this paper we propose a taxonomy that identifies and structures various types of data related to energy applications. The taxonomy can be used to guide application specific data model development for training machine learning models. Focusing on a household electricity forecasting application, we validate the effectiveness of the proposed taxonomy in guiding the selection of the features for various types of models. As such, we study of the effect of domain, contextual and behavioral features on the forecasting accuracy of four interpretable machine learning techniques and three openly available datasets. Finally, using a feature importance techniques, we explain individual feature contributions to the forecasting accuracy.
Accurately localizing the brain regions that triggers seizures and predicting whether a patient will be seizure-free after surgery are vital for surgical planning and patient management in drug-resistant epilepsy. Stereo-electroencephalography (sEEG) delivers high-fidelity intracranial recordings that enable clinicians to precisely locate epileptogenic networks. However, the clinical identification is subjective and dependent on the expertise of the clinical team. Data driven approaches in this domain are sparse, despite the fact that sEEG offers high temporal-fidelity related to seizure dynamics that can be leveraged using graph structures ideal for imitating brain networks. In this study, we introduce a dual-task graph-neural network (GNN) framework that operates on windowed sEEG recordings to jointly predict seizure-freedom outcomes and identify seizure-onset-zone (SOZ) channels. We assemble non-overlapping 10 second windows from 51 clinical seizures spread across 20 pediatric patients, with sEEG data annotated by clinical experts. For each temporal window we construct a functional connectivity graph via thresholded Pearson correlations and extract rich node features (spectral, statistical, wavelet, Hjorth and local graph features), alongside six global graph descriptors. We optimize a combined cross-entropy loss with a tunable task-weight, and select model hyper-parameters via Optuna. Under window-level 10-fold cross-validation, the model achieves a mean graph-level accuracy of $89.31 \pm 0.0976 \%$ for seizure-freedom prediction and a node-level SOZ localization accuracy of $94.72. \pm 0.0041 \%$. For the best performing model, we ran additive and leave-one-out ablation studies to explore feature importance for graph and node-level accuracy.
Probing techniques have shown promise in revealing how LLMs encode human-interpretable concepts, particularly when applied to curated datasets. However, the factors governing a dataset's suitability for effective probe training are not well-understood. This study hypothesizes that probe performance on such datasets reflects characteristics of both the LLM's generated responses and its internal feature space. Through quantitative analysis of probe performance and LLM response uncertainty across a series of tasks, we find a strong correlation: improved probe performance consistently corresponds to a reduction in response uncertainty, and vice versa. Subsequently, we delve deeper into this correlation through the lens of feature importance analysis. Our findings indicate that high LLM response variance is associated with a larger set of important features, which poses a greater challenge for probe models and often results in diminished performance. Moreover, leveraging the insights from response uncertainty analysis, we are able to identify concrete examples where LLM representations align with human knowledge across diverse domains, offering additional evidence of interpretable reasoning in LLMs.