Feature Attribution

Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on attributing importance to static input features at a single point in time, and thus fail to generalize to sequential decision-making settings. This paper fills this gap by introducing techniques to generate attribution-based explanations for Markov Decision Processes (MDPs). We give a formal characterization of what attributions should represent in MDPs, focusing on explanations that assign importance scores to both individual states and execution paths. We show how importance scores can be computed by leveraging techniques for strategy synthesis, enabling the efficient computation of these scores despite the non-determinism inherent in an MDP. We evaluate our approach on five case-studies, demonstrating its utility in providing interpretable insights into the logic of sequential decision-making agents.

Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering meaningful molecular mechanisms remains unclear. Here, we systematically evaluate four widely used approaches: Saliency Attribution (SA), Integrated Gradients (IG), GNNExplainer, and Layer-wise Relevance Propagation (LRP) for identifying disease-relevant structure in breast cancer RNA-seq data projected onto a protein-protein interaction network. Using synthetic benchmarks with known ground-truth motifs, we show that explanation methods recover distinct signal organizations: SA performs best for sparse single-node drivers, whereas IG and LRP preferentially recover distributed pathway-like and cascade-like signals. In TCGA BRCA data, we identify a consistent topological signature of disease-associated hubs in which attribution peaks in the immediate 1-hop neighborhood and decays across successive network shells, a pattern most pronounced for IG and LRP and associated with strong enrichment of known cancer hubs. We further observe a trade-off between local hub enrichment and global gene ranking performance, with IG optimizing local enrichment and SA achieving superior global discrimination. Motivated by these complementary behaviors, we introduce a framework combining a shell-based hub score with consensus ranking across explainers. Consensus scores improve prioritization of canonical cancer genes (TP53, BRCA1, ESR1, MYC), reduce dependence on node degree, and, especially when tuned, outperform individual methods. Pathway enrichment further reveals improved recovery of biologically coherent cancer programs, including ERBB2, RTK, MAPK, immune, and cytokine signaling. Together, these results demonstrate that topology-aware integration of graph explanations can improve biological interpretability and biologically relevant molecular recovery.

Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and interpolation schedule in predictive distribution space. FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher-Rao geodesic on the probability simplex. The corresponding input-space trajectory is realized through the pullback Fisher metric and stabilized by KL and Euclidean trust regions; attributions are obtained by integrating input gradients along this trajectory. Across six ImageNet architectures, FRInGe most clearly improves calibration-oriented attribution metrics, especially MAS scores, while remaining competitive on perturbation AUC and infidelity.

End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and hard-to-localize risks. Existing methods either rely on auxiliary monitoring models or generate textual explanations, but are decoupled from the planning process and fail to reveal the visual evidence underlying trajectory generation. While attribution offers a direct alternative, planning differs from image classification by taking six-view camera images as input and predicting continuous multi-step trajectories, requiring attribution to capture both critical views and regions and their influence on outputs. Moreover, whether attribution maps can support risk identification remains underexplored. To address this, we propose a hierarchical attribution framework for end-to-end planning. Specifically, using L2 consistency with the original trajectory as the objective, we design a coarse-to-fine region attribution strategy that searches candidate regions across the full six-view input and refines attribution within them. We further extract three attribution statistics as predictive signals for planning risk, including attribution entropy to measure how concentrated the planner's reliance is over the joint visual space, within-camera spatial variance to characterize how spread out the attribution is within each view, and cross-camera Gini coefficient to quantify how unevenly attribution is distributed across the six cameras. Experiments on BridgeAD, UniAD, and GenAD show that these statistics correlate with planning risk, achieving Spearman correlations of $0.30 \pm 0.07$ with trajectory error and AUROC of $0.77 \pm 0.04$ for collision detection. The signal generalizes to held-out scenes with negligible degradation and remains stable under an alternative attribution baseline.

Attribution methods explain which input features drive a model's prediction, making them central to model debugging and mechanistic interpretability. Yet backward attribution methods, including gradients, LRP, and transformer-specific rules, lack a shared framework in which to compare the underlying backward calculations. We introduce such a framework by recasting backward attribution as a two-player game on an extended network graph, building on Gaubert and Vlassopoulos' ReLU Net Game. Gradients and the full alpha-beta-LRP family arise as integrals over game trajectories under specific equilibria, so attribution maps become projections of trajectory distributions rather than the primary object. Desired explanation properties, such as localisation focus, robustness to input noise, or stable attention routing, can be specified as game-theoretic concepts, including policy regularization, risk aversion, and extended action sets, and translate directly into novel adaptations of the well-known backward rules. On ViT-B/16, one such selected adaptation of alpha-beta-LRP outperforms prior transformer-specific backward methods across all considered localisation metrics.

We study the efficient computation of Shapley values for product games -- cooperative games in which the coalition value factorizes as a product of per-player terms. Such games arise in machine learning explainability whenever the value function inherits a multiplicative structure from the underlying model, as in kernel methods with product kernels and tree-based models. Our key result is that the Shapley value of each player in a product game admits an exact one-dimensional integral representation: the weighted sum over exponentially many feature coalitions collapses to the integral of a degree-$(d-1)$ polynomial over $[0,1]$, where $d$ is the total number of features. This yields a Gauss--Legendre quadrature scheme that is provably exact whenever the number of nodes satisfies $m_q \geq \lceil d/2 \rceil$, and otherwise provides a near-exact approximation with error provably decaying geometrically in $m_q$. In practice, a few hundred nodes can achieve highly precise estimates even with thousands of features. Building on this formulation, we derive a numerically stable implementation via log-space evaluation, together with an efficient parallel implementation based on associative scan primitives that achieves $O(d\,m_q)$ total work and $O(\log d)$ parallel time. Experiments show that QuadraSHAP is the fastest numerically stable method across all tested configurations.

The main XAI attribution methods for deep neural networks -- GradCAM, SHAP, LIME, Integrated Gradients -- operate on separate theoretical foundations and are not formally comparable. We present GRALIS (Gradient-Riesz Averaged Locally-Integrated Shapley), a mathematical framework establishing a representation theory for attributions: every additive, linear, and continuous attribution functional on L^2(Q,mu) admits a unique canonical representation (Q, w, Delta), proved necessary by the Riesz Representation Theorem. This class encompasses SHAP, IG, LIME and linearized GradCAM, but excludes nonlinear functionals such as standard GradCAM or attention maps. Seven formal theorems provide simultaneous guarantees absent in any individual method: (T1) necessary canonical form; (T2) exact completeness; (T3) Monte Carlo convergence O(1/sqrt(m))+O(1/k); (T4) exact Shapley Interaction Values; (T5) Hoeffding ANOVA decomposition; (T6) Sobol sensitivity generalization; (T7) multi-scale extension (MS-GRALIS) with minimum-variance weights. An algebraic appendix justifies the GRALIS-SIV correspondence via the Mobius transform without circularity. GRALIS satisfies 13.5/14 axiomatic properties vs. 2.5-6/14 for individual methods, including completeness, sensitivity, locality, order-k interactions and optimal multi-scale aggregation simultaneously. Preliminary validation on BreaKHis (1,187 histology images, DenseNet-121) reports deletion faithfulness AUC +0.015 (malignant), 96% class-conditional consistency, SAL = 0.762+/-0.109 and sparsity index 0.39. Extended comparison with baseline XAI methods is planned for a companion paper.

Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologists to visualize deformities in medical imaging. Most of the existing visualization techniques are based on discriminative models and highlight regions of the input image participating in the decision-making of a classifier. However, these approaches do not take all noticeable objects into account as their objective is to classify the input by using a minimal set of discriminative features. To overcome the issue, a counterfactual explanation (CX) based class-oriented feature attribution method is proposed. A counterfactual explanation (CX) explicates a causal reasoning process of the form: "if X had not happened, then Y would not have happened". The method is built on generative adversarial networks (GANs) with a cyclical-consistent loss function. We evaluate our method on three datasets: synthetic, tuberculosis and BraTS. All experiments confirm the efficacy of the proposed method. This study also highlighted the limitations of existing counterfactual explanation techniques in producing plausible counterfactual instances (CIs). Accompanying CXs with believable CIs thus provides self-explanatory analogy-based explanations. To this end, a CI generation method is proposed. Also, a novel technique is used to evaluate the quality of CI. The baseline results are produced on the BraTS dataset.

The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory tests or prescribing medications the most. We conduct our analysis on data and decisions extracted from electronic health records of 4486 post-surgical cardiac patients. The summary statistics for 335 different lab order decisions and 407 medication decisions are reported. We show that in many cases, physician's lab-order and medication decisions can be well predicted from a small subset of all features.

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive their predictions. Existing global GNN explainers operate at the structural level identifying recurring subgraph motifs, but none explain model behaviour globally at the level of input node attributes. We propose GRAFT, a posthoc global explanation framework that identifies class-level feature importance profiles for GNNs. The method combines diversity-guided exemplar selection, Integrated Gradients-based attribution, and aggregation to construct a global view of feature influence for each class, which can be further expressed as concise natural language rules using a large language model with self-refinement. We evaluate GRAFT across multiple datasets, architectures, and experimental settings, demonstrating its effectiveness in capturing model-relevant features, supporting bias analysis, and enabling feature-efficient transfer learning. In addition, we introduce a structured human evaluation protocol to assess the interpretability of generated rules along dimensions such as accuracy and usefulness. Our results suggest that GRAFT provides a practical and interpretable approach for analysing feature-level behaviour in GNNs, bridging quantitative attribution with human-understandable explanations.

Spectral-based machine learning models have been increasingly deployed in chemometrics and spectroscopy, where predictive accuracy is as important as explainability. Current employed eXplainable Artificial Intelligence (XAI) methods are largely adapted from tabular or generic multivariate domains, assigning relevance to isolated spectral variables rather than to the chemically meaningful spectral zones. Widely adopted tools such as SHapley Additive exPlanations (SHAP), Permutation Feature Importance (PFI), and Variable Importance in Projection scores (VIP) were not designed for the physical continuity and high collinearity of spectral data, and their variable-level outputs require post-hoc aggregation to recover zone-level information. This study introduces the Spectral Model eXplainer (SMX), a post-hoc, global, model-agnostic XAI framework that explains spectral classifiers through expert-informed spectral zones. SMX summarizes each zone via PCA, defines quantile-based logical predicates, estimates predicate relevance with perturbation in stochastic subsamples, and aggregates bag-wise rankings in a directed weighted graph summarized by Local Reaching Centrality. A key component is threshold spectrum reconstruction, which back-projects predicate boundaries to the original spectral domain in natural measurement units, enabling direct visual comparison with measured spectra. The method was evaluated on eight real spectral datasets (six based on X-ray Fluorescence--XRF and two based on Gamma-ray Spectrometry) and one synthetic benchmark with known gr

Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield unreliable explanations when the integration path between a baseline and the input passes through regions with noisy gradients. While Guided Integrated Gradients reduces this sensitivity by adaptively updating low-gradient-magnitude features, input-space guidance still produces intermediate inputs that deviate from the data manifold. To address this limitation, we propose Manifold-Aligned Guided Integrated Gradients (MA-GIG), which constructs attribution paths in the latent space of a pre-trained variational autoencoder. By decoding intermediate latent states, MA-GIG biases the path toward the learned generative manifold and reduces exposure to implausible input-space regions. Through qualitative and quantitative evaluations, we demonstrate that MA-GIG produces faithful explanations by aggregating gradients on path features proximal to the input. Consequently, our method reduces off-manifold noise and outperforms prior path-based attribution methods across multiple datasets and classifiers. Our code is available at https://github.com/leekwoon/ma-gig/.

In recent years, several advances have been observed in Deep Learning with surprising results. Models in this area have been increasingly used in numerous applications, including those sensitive to human life, which require clear explanations and justifications. Various explainability methods have been proposed, but not many metrics to evaluate these methods. The most commonly used metric is the Intersection over Union (IoU). However, due to the characteristics of the results of the explainability methods, called saliency maps, which do not have a known shape, we hypothesise that there must be a better metric that allows one to find an explainability method that produces results that best resemble the human perception. We propose using different metrics to assess the similarity between human perception and the explanation saliency maps to find a better metric. An investigation was conducted employing a subset of the Chihuahuas images from ImageNet dataset. Several CAM-based explainability methods were used to generate saliency maps for each chihuahua image. Alignment was measured by applying distance metrics between the bounding box of human annotations and the saliency maps produced by each explainability method. Rankings of the best saliency maps were created using the results of the distance metrics and compared to the ranking obtained using people's choice, collected through crowdsourcing, of the best explanation saliency maps for each selected image. Comparison between rankings was performed using the Rank-Biased Overlap (RBO) metric. The results indicate the feasibility of our method to find the explainability method that best resembles human perception. In our experiments, the two metrics that best resemble human perception corresponded to Manhattan and Correlation. Besides, the best explainability methods regarding human perception were LayerCAM, Score-CAM, and IS-CAM.

Explainable AI (XAI) aims to improve user understanding and decisions when using AI models. However, despite innovations in XAI, recent user evaluations reveal that this goal remains elusive. Understanding human cognition can help explain why users struggle to effectively use AI explanations. Focusing on reasoning on structured (tabular) data, we examined various reasoning strategies for different XAI methods (none, feature importance, feature attribution) in the decision task of anticipating AI decisions (i.e., forward simulation). We i) elicited reasoning strategies from a formative user study, and ii) collected decisions from a summative user study. Using cognitive modeling, we implemented the processes underlying each reasoning strategy and evaluated their alignment with human decision-making. We found that our models better fit human decisions than baseline machine learning proxies, providing insights into which reasoning strategies are (in)effective. We then demonstrate how the fitted model can be used to form hypotheses and investigate research questions that are costly to study with real human participants. This work contributes to debugging human understanding of XAI, informing the future development of more usable and interpretable AI explanations.

Deep learning models for 12-lead electrocardiogram (ECG) analysis achieve high diagnostic performance but lack the intuitive interpretability required for clinical integration. Standard feature attribution methods are limited by the inherent difficulty in mapping abstract waveform fluctuations to physical anatomical pathologies. To resolve this, we propose a cross-modal method that projects feature attributions from high-performance 12-lead ECG models onto the CineECG 3D anatomical space. Our study reveals that while models trained directly on CineECG signals suffer from reduced accuracy and incoherent attributions, the proposed mapping mechanism effectively recovers clinically relevant feature rankings. Validated against a ground-truth dataset of 20 cases annotated by domain experts, the mapped explanations yield a Dice score of 0.56, significantly outperforming the 0.47 baseline of standard 12-lead attributions. These findings indicate that cross-modal averaging mapping effectively filters attribution instability and improves the localization of pathological features, combining the diagnostic expressiveness of standard ECG with the intuitive clarity of anatomical visualization.

When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to infer where an image was captured. Whether image geolocation models rely on similar object-level evidence remains difficult to determine, as attribution methods like Grad-CAM typically highlight diffuse regions rather than coherent visual entities, making it difficult to link model predictions to specific objects or perceptible patterns. In this work, we propose an object-centric analysis pipeline to investigate the visual evidence used by geolocation models. Starting from attribution maps, we extract salient regions and segment them into object-like elements. We evaluate their predictive relevance through deletion and insertion tests, comparing attributionguided crops to randomly selected regions with similar coverage. Experiments on a three-country benchmark show that attribution-guided crops consistently retain more information for the model's prediction than random crops. These results suggest that attribution maps can be decomposed into interpretable, perceptible elements, providing a step toward object-level analysis of geolocation models.

We investigate the explanability properties of the recently proposed linear-min-max neural networks. At initialization, they can be interpreted as k-medoids with the infinity norm as a distance. Then, they are trained using subgradient descent to better fit the data. The model has been shown to be a universal approximator. Yet, we can trace the decision process because a single most activated neuron is responsible for the value of the output. Using this property, we designed a pixel fragility measure that determines whether changes to a single pixel may be responsible to a change in the classification output. Experiments on the PneumoniaMnist dataset show that this explanation for the output of the neural network compares favorably to SHAP and Integrated Gradient.

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive Learning (CL). Instead of explicitly operating a classification, CL has the NN produce an embedding space where projections of similar data are pulled together, while projections of dissimilar data are pushed apart. In the case of Supervised CL (SCL), labels are adopted as similarity criteria, thus creating an embedding space where the projected data points are well-clustered. SCL provides crucial advantages over CE with regard to adversarial robustness and out-of-distribution detection, thus making it a more natural choice in safety-critical scenarios. In the present paper, we empirically show that NNs for image classification trained with SCL present higher-quality feature attribution explanations than CL with regard to faithfulness, complexity, and continuity. These results reinforce previous findings about CL-based approaches when targeting more trustworthy and transparent NNs and can guide practitioners in the selection of training objectives targeting not only accuracy, but also transparency of the models.

Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely on marginal effects, overlooking feature interactions, where groups of features jointly influence model output. Such interactions are especially important in image classification tasks, where semantic meaning often arises from pixel interdependencies rather than isolated features. Existing interaction-based methods for images are either coarse (e.g., superpixel-only) or, fail to satisfy core interpretability axioms. In this work, we introduce H-Sets, a novel two-stage framework for discovering and attributing higher-order feature interactions in image classifiers. First, we detect locally interacting pairs via input Hessians and recursively merge them into semantically coherent sets; segmentation from Segment Anything (SAM) is used as a spatial grouping prior but can be replaced by other segmentations. Second, we attribute each set with IDG-Vis, a set-level extension of Integrated Directional Gradients that integrates directional gradients along pixel-space paths and aggregates them with Harsanyi dividends. While Hessians introduce additional compute at the detection stage, this targeted cost consistently yields saliency maps that are sparser and more faithful. Evaluations across VGG, ResNet, DenseNet and MobileNet models on ImageNet and CUB datasets show that H-Sets generate more interpretable and faithful saliency maps compared to existing methods.

Large Language Models (LLMs) fine-tuned on serialized tabular data are emerging as powerful alternatives to traditional tree-based models, particularly for heterogeneous or context-rich datasets. However, their deployment in high-stakes domains is hindered by a lack of faithful interpretability; existing methods often rely on global linear proxies or scalar probability shifts that fail to capture the model's full probabilistic uncertainty. In this work, we introduce TabSHAP, a model-agnostic interpretability framework designed to directly attribute local query decision logic in LLM-based tabular classifiers. By adapting a Shapley-style sampled-coalition estimator with Jensen-Shannon divergence between full-input and masked-input class distributions, TabSHAP quantifies the distributional impact of each feature rather than simple prediction flips. To align with tabular semantics, we mask at the level of serialized key:value fields (atomic in the prompt string), not individual subword tokens. Experimental validation on the Adult Income and Heart Disease benchmarks demonstrates that TabSHAP isolates critical diagnostic features, achieving significantly higher faithfulness than random baselines and XGBoost proxies. We further run a distance-metric ablation on the same test instances and TabSHAP settings: attributions are recomputed with KL or L1 replacing JSD in the similarity step (results cached per metric), and we compare deletion faithfulness across all three.

Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their behavior on commonly used benchmarks underexplored. To address this gap, we study contrastive, LRP-based attribution as a practical tool for analyzing LLM failures in realistic settings. We formulate failure analysis as contrastive attribution, attributing the logit difference between an incorrect output token and a correct alternative to input tokens and internal model states, and introduce an efficient extension that enables construction of cross-layer attribution graphs for long-context inputs. Using this framework, we conduct a systematic empirical study across benchmarks, comparing attribution patterns across datasets, model sizes, and training checkpoints. Our results show that this token-level contrastive attribution can yield informative signals in some failure cases, but is not universally applicable, highlighting both its utility and its limitations for realistic LLM failure analysis. Our code is available at: https://aka.ms/Debug-XAI.

Root cause analysis (RCA) for time-series anomaly detection is critical for the reliable operation of complex real-world systems. Existing explanation methods often rely on unrealistic feature perturbations and ignore temporal and cross-feature dependencies, leading to unreliable attributions. We propose a conditional attribution framework that explains anomalies relative to contextually similar normal system states. Instead of using marginal or randomly sampled baselines, our method retrieves representative normal instances conditioned on the anomalous observation, enabling dependency-preserving and operationally meaningful explanations. To support high-dimensional time-series data, contextual retrieval is performed in learned low-dimensional representations using both variational autoencoder latent spaces and UMAP manifold embeddings. By grounding the retrieval process in the system's learned manifold, this strategy avoids out-of-distribution artifacts and ensures attribution fidelity while maintaining computational efficiency. We further introduce confidence-aware and temporal evaluation metrics for assessing explanation reliability and responsiveness. Experiments on the SWaT and MSDS benchmarks demonstrate that the proposed approach consistently improves root-cause identification accuracy, temporal localization, and robustness across multiple anomaly detection models. These results highlight the practical utility of conditional attribution for explainable anomaly diagnosis in complex time-series systems. Code and models are available at: https://github.com/dfki-av/Conditional-Attribution-for-Root-Cause-Analysis-in-Time-Series-Anomaly-Detection.

Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors. To address this, we introduce the first CLT-native end-to-end pruning framework, PIE, which pioneers the paradigm of pruning first and interpreting later. PIE connects Pruning, automatic Interpretation, and interpretation Evaluation, establishing a comprehensive benchmarking environment to systematically measure behavioral fidelity and downstream interpretability under pruning. Within this framework, we adapt strong relevance baselines and propose Feature Attribution Patching (FAP), a patch-grounded attribution method that scores CLT features by aggregating gradient-weighted write contributions. Furthermore, we introduce FAP-Synergy, a systematic synergy-aware reranking procedure. We evaluate pruning using KL-divergence behavior retention and assess interpretation quality with FADE-style metrics across IOI and Doc-String datasets. Across budget constraints of K in {50, 100, 200, 400, 800}, our rigorous benchmarking reveals distinct operational regimes: while base FAP and adapted baselines perform robustly at relaxed budgets, FAP-Synergy excels in highly constrained, strict-budget regimes. Crucially, we demonstrate a practical "Effective Budget" advantage: on the IOI task for both Llama-3.2-1B and Gemma-2-2B, FAP-Synergy at K=50 functionally matches the behavioral fidelity of baseline circuits at K=75. Because downstream evaluation costs scale linearly per feature, Synergy effectively grants the pipeline 25 "free" features, achieving K=75 fidelity while reducing interpretation costs by 33%.

Masking-based post-hoc explanation methods, such as KernelSHAP and LIME, estimate local feature importance by querying a black-box model under randomized perturbations. This paper formulates this procedure as communication over a query channel, where the latent explanation acts as a message and each masked evaluation is a channel use. Within this framework, the complexity of the explanation is captured by the entropy of the hypothesis class, while the query interface supplies information at a rate determined by an identification capacity per query. We derive a strong converse showing that, if the explanation rate exceeds this capacity, the probability of exact recovery necessarily converges to one in error for any sequence of explainers and decoders. We also prove an achievability result establishing that a sparse maximum-likelihood decoder attains reliable recovery when the rate lies below capacity. A Monte Carlo estimator of mutual information yields a non-asymptotic query benchmark that we use to compare optimal decoding with Lasso- and OLS-based procedures that mirror LIME and KernelSHAP. Experiments reveal a range of query budgets where information theory permits reliable explanations but standard convex surrogates still fail. Finally, we interpret super-pixel resolution and tokenization for neural language models as a source-coding choice that sets the entropy of the explanation and show how Gaussian noise and nonlinear curvature degrade the query channel, induce waterfall and error-floor behavior, and render high-resolution explanations unattainable.

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks, yet a reasoning trace may merely accompany the final answer rather than causally contribute to it or faithfully reflect how it was reached. We introduce differentiable attention manipulation to train salient reasoning with reinforcement learning -- method which we call AtManRL. By optimizing an additive attention mask that identifies the CoT tokens needed to recover the model's answer, we derive a saliency reward and combine it with an outcome reward in GRPO with decoupled advantages. Because both saliency and faithfulness depend strongly on trace length, we evaluate against a sweep of length-penalty baselines that traces the trade-off a pure length penalty can reach, rather than against a single baseline. Across three models (Qwen2.5-3B, Granite-3.3-2B, and Phi-4-mini) and four benchmarks (GSM8K, MMLU, ProofWriter, and QuestBench), AtManRL sits above this trade-off curve by 3.9-4.0pp in saliency, measured as answer changes under mistake injection, and by 5.7-7.7pp in faithfulness, measured as hint verbalization under hint injection, while matching the accuracy of baselines of similar length. These results suggest that training explicitly for saliency is a promising route towards chain-of-thought reasoning that is more faithful to the model's actual decision process.

For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such methods lack rigor and can mislead human decision-makers. In high-stakes uses of ML, the lack of rigor is especially problematic. One prime example of provable lack of rigor is the adoption of Shapley values in explainable artificial intelligence (XAI), with the tool SHAP being a ubiquitous example. This paper overviews the ongoing efforts towards using rigorous symbolic methods of XAI as an alternative to non-rigorous non-symbolic approaches, concretely for assigning relative feature importance.

Existing research on large language models (LLMs) for automated code compliance has primarily focused on performance, treating the models as black boxes and overlooking how training decisions affect their interpretive behavior. This paper addresses this gap by employing a perturbation-based attribution analysis to compare the interpretive behaviors of LLMs across different fine-tuning strategies such as full fine-tuning (FFT), low-rank adaptation (LoRA) and quantized LoRA fine-tuning, as well as the impact of model scales which include varying LLM parameter sizes. Our results show that FFT produces attribution patterns that are statistically different and more focused than those from parameter-efficient fine-tuning methods. Furthermore, we found that as model scale increases, LLMs develop specific interpretive strategies such as prioritizing numerical constraints and rule identifiers in the building text, albeit with performance gains in semantic similarity of the generated and reference computer-processable rules plateauing for models larger than 7B. This paper provides crucial insights into the explainability of these models, taking a step toward building more transparent LLMs for critical, regulation-based tasks in the Architecture, Engineering, and Construction industry.

We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is mathematically equivalent to path-weighted integrated gradients, provided the weighting function matches the cumulative distribution function of the sampling density. This equivalence allows the stochastic expectation to be evaluated via a deterministic Riemann sum, improving the error convergence rate from $O(m^{-1/2})$ to $O(m^{-1})$ for smooth models. Furthermore, we demonstrate analytically that PS-IG functions as a variance-reducing filter against gradient noise - strictly lowering attribution variance by a factor of 1/3 under uniform sampling - while preserving key axiomatic properties such as linearity and implementation invariance.

Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and deployment in real-world systems. This paper presents an applied comparative study of three explainability techniques: Integrated Gradients, Attention Rollout, and SHAP, on a fine-tuned DistilBERT model for SST-2 sentiment classification. Rather than proposing new methods, the focus is on evaluating the practical behavior of existing approaches under a consistent and reproducible setup. The results show that gradient-based attribution provides more stable and intuitive explanations, while attention-based methods are computationally efficient but less aligned with prediction-relevant features. Model-agnostic approaches offer flexibility but introduce higher computational cost and variability. This work highlights key trade-offs between explainability methods and emphasizes their role as diagnostic tools rather than definitive explanations. The findings provide practical insights for researchers and engineers working with transformer-based NLP systems. This is a preprint and has not undergone peer review.

Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances in deep learning, most medical AI systems operate as opaque black boxes, providing little insight into why a particular diagnosis was reached. In this paper, we introduce Med-CAM, a framework for generating minimal and sharp maps as evidence-based explanations for Medical decision making via Classifier Activation Matching. Med-CAM trains a segmentation network from scratch to produce a mask that highlights the minimal evidence critical to model's decision for any seen or unseen image. This ensures that the explanation is both faithful to the network's behaviour and interpretable to clinicians. Experiments show, unlike prior spatial explanation methods, such as Grad-CAM and attention maps, which yield only fuzzy regions of relative importance, Med-CAM with its superior spatial awareness to shapes, textures, and boundaries, delivers conclusive, evidence-based explanations that faithfully replicate the model's prediction for any given image. By explicitly constraining explanations to be compact, consistent with model activations, and diagnostic alignment, Med-CAM advances transparent AI to foster clinician understanding and trust in high-stakes medical applications such as pathology and radiology.