Explainability Evaluation

Follow this topic Ask about this topic

Momentum

27 papers in the last four weeks, up 50% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 218

Oct 7, 2026cs.LG

How to train your model organism

Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox interpretability techniques. We argue that the prevailing practice of training model organisms to a single objective of installing the target behavior is insufficient and propose validating model organisms with respect to three objectives with associated metrics: target-behavior installation, general-capability preservation (i.e., parametric knowledge, chat quality), and output naturalness (i.e., CoT and activations). We re-visit two publicly released organism suites using this validation framework and show that (1) chat quality and CoT naturalness degrade substantially across training recipes, and (2) validation metrics predict how well interpretability methods recover the installed behavior, e.g., a logit lens readout covaries with an organism's general capabilities. We introduce a multi-objective training approach based on model merging to train more realistic model organisms. Finally, on a new suite of model organisms targeting demographic biases in clinical reasoning, we compare training recipes and find that DPO training stays closer to the base model than supervised finetuning, and the proposed model optimization approach better preserves capabilities and naturalness. Auditing this suite with an investigator agent, we again observe validation metrics tracking bias recovery. In sum, training methods shape the interpretability conclusions an organism supports, and we argue that one should consider multiple objectives to draw generalizable conclusions about interpretability methods using (realistic) model organisms.

Xilin Wang, David Bau, Byron C. Wallace

Northeastern University Boston, MA 02115, USA

Mechanistic Interpretability Explainability Evaluation Multi-Objective Optimization

Oct 4, 2026cs.LG

Does Explainability Survive Data Drift?

Model performance monitoring is a standard practice in machine learning deployments. Detection performance is tracked continuously, and model decay is expected as the relationship between the feature and target variables degrades, a phenomenon known as concept drift. Explanation fidelity, however, is rarely monitored with the same discipline, even in domains such as financial systems, healthcare, and other regulated environments where explanations are required for governance purposes. This paper investigates whether explanations can decay under data drift, even when the feature-target relationship remains stable, and whether explanations produced before drift occurs remain faithful to the decisions of the model that replaces them. Using the IEEE-CIS Transaction Fraud Detection dataset, we find statistically significant covariate shift but no statistically significant evidence of concept drift under the implemented conditional-drift tests, thereby providing an empirical setting in which input distributional change can be studied separately from detectable changes in the feature-target relationship. Local explanations are generated with ExIFFI and evaluated at three levels: path validity, structural behaviour, and fidelity under controlled intervention. Results show that while prior explanations retain substantial decision relevance to a retrained model, they are consistently less faithful than newly generated explanations, with no evidence of a systematically widening gap across the evaluated windows. The study shows that explanation fidelity requires its own monitoring, that structural stability of explanations does not guarantee functional fidelity, and that explanations should be treated as artifacts tied to the model that produced them.

Samuel Ozechi

Explainability Evaluation

Oct 1, 2026cs.AI

A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification

A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification of medical abstracts. The work addresses the disagreement problem in Explainable Artificial Intelligence, where different attribution methods produce divergent explanations for the same input and prediction. A natural language inference engine is implemented over the Medical Abstracts corpus with five enriched hypotheses per diagnostic category and a balanced sample of one thousand texts per class. Five explanation methods are compared: SHAP and LIME as model-agnostic approaches, occlusion and Input x Gradient as deep-learning-specific approaches, and Attention x Gradient as a transformer-specific approach. Explanations are standardized through top-token attribution, and pairwise agreement is quantified using the Jaccard index. High predictive accuracy is achieved across well-defined clinical domains, whereas performance degrades under high semantic ambiguity. Explanatory stability directly mirrors predictive certainty, exhibiting strong convergence in univalent categories and a marked drop under diagnostic uncertainty. Furthermore, qualitative error auditing uncovers three systemic failure mechanisms: lexical hypersensitivity, semantic overlap, and loss of attribution coherence. The results support the combined use of several explanation methods and quantitative agreement metrics when auditing transformer-based models in medical text classification, and suggest prioritizing specific clinical ontologies over broad diagnostic labels.

Javier Diaz Esteban-Herreros, David Muñoz-Valero, Raquel Martínez-España +2

Department of Technologies and Information Systems, Universidad de Castilla-La Mancha, Avenida Carlos III, s/n, Toledo, 45071, Spain · University of Murcia, Avenida Teniente Flomesta, 5, Murcia, 3003, Spain · Murcian Bio-Health Institute (IMIB-Arrixaca), Pabellón Docente del Hospital Clínico Universitario Virgen de la Arrixaca, Murcia, 3120, Spain

Transformer Interpretability Perturbation-Based Feature Attribution Explanation Stability Explainability Evaluation

Oct 1, 2026cs.LG

Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

Mechanistic interpretability aims to recover the internal computations responsible for model behavior. Progress in automated circuit discovery is often framed as a search problem: better attribution or optimization should identify better mechanisms. This assumes that the evaluation objective can recognize a better circuit once it is found. We show that intervention-defined faithfulness can instead prefer an equally sized circuit that reproduces the model's behavior less well, creating an objective-level recovery gap. Across four human-reference tasks and InterpBench, we compare validation faithfulness with behavior on held-out prompts under fixed ordinary resampling. The behavioral criterion is agreement with the intact model, including its mistakes, except on Greater-Than, where we use semantic accuracy. Controlled reference edits reveal misranking without any discovery algorithm, and outputs of EAP, EAP-IG, ACDC, and Edge-SP exhibit the same failure. Under resampling, KL misranks 9.4%-41.2% of candidate pairs across these methods on the human-reference tasks. We investigate context distortion as an explanation: replacing excluded signals changes the inputs on which retained components operate. Restoring selected signals from the recipient's intact-model execution repairs 96 of 100 persistent KL misrankings from the discovery pool on both validation and held-out prompts. The circuits and their original behavioral scores remain unchanged. These findings show why better discovery alone is insufficient when its objective rewards the wrong candidate.

Chuqin Geng, Li Zhang, Haolin Ye +3

University of Toronto · McGill University

Circuit Discovery Mechanistic Interpretability Explainability Evaluation

Oct 1, 2026cs.LG

MCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees

Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive information can be distributed across correlated predictors. Existing methods such as SHAP, LIME, HSIC, MI/CMI, and SAGE may therefore produce unstable rankings under multicollinearity or near-duplicate predictors. We propose the Mutual Correlation Impact Ratio Method (MCIR-M), a dependence-aware global feature-importance approach that quantifies the unique predictive information contributed by each feature beyond a selected dependence neighbourhood. MCIR-M introduces the Mutual Correlation Impact Ratio (MCIR), which conditions each feature on strongly dependent neighbours and computes a normalized ratio of conditional to block-level information. The population score lies in [0,1] and equals zero under exact conditional redundancy. We also introduce a lightweight estimation procedure that computes MCIR using a fraction of the available data and evaluates agreement with full-data explanations. Across controlled synthetic redundancy experiments and the UCI HAR benchmark, MCIR shows dependence-aware ranking behaviour, with its clearest advantage under injected near-duplicate predictors. Comparisons with independent and conditional SHAP, SAGE, HSIC, MI-based scores, and CIR-family baselines are mixed across real-data criteria. Reduced explanation samples lower computational burden in the evaluated configurations, while agreement with full-data explanations is assessed separately through ranking, head-set, and faithfulness diagnostics. Overall, MCIR-M provides a practical dependence-aware diagnostic for global explanation under strong feature dependence.

Poushali Sengupta, Sabita Maharjan, Frank Eliassen +2

Department of Informatics, University of Oslo Oslo, Norway · Department of Electronic Systems, Aalborg University Aalborg, Denmark

Feature Attribution Explainability Evaluation

Sep 30, 2026cs.LG

WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing

When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer has failed or the model has learned a shortcut. We introduce WOMBAT, a benchmark of 14 whitebox GNNs, each with message-passing weights set by hand to detect a specific SMARTS motif. Each model's decision rule is known by construction, providing attribution ground truth against which explainer errors can be identified and studied. We validate the models on millions of PubChem molecules and evaluate post-hoc explainers including GNNExplainer, PGExplainer, and Integrated Gradients. Guided by our qualitative analysis, we construct a model that causes Integrated Gradients to spread attribution across the graph, even though the model reliably detects the intended motif. We release the dataset, models, and evaluation code to help researchers in the development of newer XAI tools for GNNs.

Dominik Matuszek, Bartosz Zieliński, Tomasz Danel +1

Jagiellonian University, Faculty of Mathematics and Computer Science · Jagiellonian University, Doctoral School of Exact and Natural Sciences · Jagiellonian University, Jagiellonian Center for Artificial Intelligence +2

Gradient-Based Attribution Explainability Evaluation GNN Explainability

Sep 28, 2026cs.LG

Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?

Mechanistic interpretability (MI) aims to explain a model's behaviour through analyzing its internal computations; circuit-based explanations aim to isolate these computations with compact subnetworks validated by ablating the rest of the model. We show that circuits validated this way may fail to recover the underlying mechanism of the model's behaviour by closely reproducing its successful decisions while failing to account for most of its errors. Such explanations should account for the model's particular errors as well as its successes. We evaluate this requirement by measuring exact answer agreement separately on model successes and failures, across circuit sizes and ablation settings, on IOI, Docstring, and six model-task settings from the Mechanistic Interpretability Benchmark. We discover that many tested circuits closely replicate correct behaviour while missing most of the model's errors. On indirect object identification (IOI) for GPT-2 small, under mean ablation, the manual circuit and tested automated circuits, including one trained against the model's full output distribution, agree with the model on 97.3-99.5% of prompts it answers correctly but only 11.4-41.7% of errors. An IOI case study shows that lost errors are recoverable by restoring omitted attention-heads which raise error reproduction from 14.2% to 75.1% on a separate held-out set with 0.41 percentage point decrease on correct agreement, exceeding matched random extensions and scalar-biased control. Intervention traces show how omitted computations produce specific wrong answers for a reproducible subset of errors. In all, these findings show circuits can preserve task success without adequately explaining model's failures, and support exact error reproduction as a necessary, but not sufficient, test of circuit-based explanations of model behaviour.

Li Zhang, Chuqin Geng, Mark Zhang +4

University of Toronto · McGill University · Tsinghua University

Faithfulness of Language Model Explanations Mechanistic Interpretability Circuits in Language Models Explainability Evaluation

Sep 28, 2026cs.CV

Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?

Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex features learned by a model into monosemantic concepts. Despite their growing popularity, evaluating their interpretability remains an active topic of research. The bedrock motivating the adoption of SAEs is the Linear Representation Hypothesis (LRH), which claims that polysemantic features can be projected onto a (near) orthogonal basis of sparse, human-understandable representations. Yet, most current frameworks evaluate proxies such as the sparsity of SAE features or the coherence of the inferred dictionary, implicitly assuming that these reflect alignment with human perception. In this paper, we provide empirical evidence that measuring the interpretability of SAE concepts is more difficult than these proxies suggest. To this end, we adapt the Autointerpretability Score (AIS) - previously shown to align with human judgments in Natural Language Processing - to vision tasks and validate our approach in a dedicated user study. We evaluate SAE concept quality using both standard metrics and our adapted AIS. We find that established interpretability metrics for SAEs correlate neither with one another nor with AIS, indicating that no single reference-free metric, whether grounded in the LRH or not, is sufficient for verifying the interpretability of vision SAEs. We argue these findings support recent calls for more verifiable, ground-truth-anchored design and evaluation of explanation methods.

Teodor Chiaburu, Franz Motzkus, Frank Haußer +1

Fraunhofer SIT · ATHENE National Research Center for Applied Cybersecurity · AUMOVIO +3

Linear Representation Hypothesis Sparse Autoencoders Mechanistic Interpretability Explainability Evaluation

Sep 28, 2026cs.LG

A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees

Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in how they define and represent concepts and connect them to model predictions. We introduce a theoretical framework that describes these approaches in a common mathematical language and supports a shared analysis of their properties. For concept discovery, which identifies concepts automatically within a latent space of a trained model, we employ a concept autoencoder view. An encoder extracts concept representations from the model's latent space, and a decoder uses them to reconstruct the original latent representation. The autoencoder's reconstruction error measures how accurately its decoder recovers the original latent representation. We revisit model completeness: how well the concepts can reproduce the model's outputs. We show that model incompleteness of the concepts can be bounded by the autoencoder's reconstruction error. The autoencoder view also provides a common way to define individual concept attributions, which measure each concept's contribution to a prediction. We establish when these attributions sum to the model's prediction, and bound the discrepancy otherwise, thus providing attribution completeness guarantees.

Vojtěch Kůr, Adam Kukučka, Tomáš Brázdil +1

Masaryk University, Faculty of Informatics, Brno, Czechia

Concept-Based Explanations Neural Network Interpretability Explainability Evaluation

Sep 25, 2026cs.LG

Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations

Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what the change is. A small perturbation of the parameters, retraining on new data, and a new architecture are different events, and each existing method is evaluated against the one it was built for. Reported robustness scores, therefore, answer different questions and cannot be compared. We propose a unified cross-family evaluation protocol that holds factual instances and generated counterfactuals fixed while testing every method against the same eight types of model change. The benchmark compares six robust methods and two standard baselines on four tabular datasets. It characterizes every changed classifier through its outputs and reports empirical robustness together with coverage, base validity, and proximity. We find that relative performance and failure modes vary across change families. Bounded parameter perturbations change 0.95% of test predictions on average, compared with 4.9% for bootstrap retraining. Methods with guarantees for these perturbations do not necessarily transfer to other changes. RobX transfers most consistently in our experiments, although greater stability can require larger interventions. We argue that robust CFE methods should be evaluated through a common protocol that specifies the model changes, measures their realized behavioral magnitude, and keeps generation performance separate from robustness.

Marcin Kostrzewa, Maciej Zięba

Department of Artificial Intelligence Wrocław University of Science and Technology

Counterfactual Evaluation Counterfactual Explanations Explainability Evaluation

Sep 23, 2026cs.LG

A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems

Sequential RecSys are central to modern personalization, exploiting user's historical interaction sequences to drive next-step decisions. Deep learning models, particularly CNN and Transformer-based architectures, have proven highly effective at capturing temporal dependencies in these histories. For transparency and trust, understanding which past interactions drive a given recommendation is increasingly important --- both for developers auditing model behavior and for users seeking a rationale. However, the non-linearities that give these models their predictive power also render them black boxes, making it difficult to attribute decisions to specific interactions. While gradient-based, perturbation-based, and attention-based explainability methods exist, a systematic benchmark of their faithfulness for sequential recommendation is missing. We address this gap by introducing a dual-model masking metric in which one model supplies per-timestep attribution scores and a separately trained, masking-robust probe measures the resulting change in predicted probability. Using this metric, we benchmark ten XAI methods across CNN, Transformer, SASRec, and BERT4Rec backbones on KuaiRand and MovieLens, complemented by analyses of temporal attribution patterns, item popularity confounding, and robustness to input corruption. Our key findings are: (1) gradient-based methods, particularly GradientSHAP and Integrated Gradients, yield the most faithful and robust attributions; (2) raw attention weights are unreliable, but gradient-weighted attention restores faithfulness on shorter sequences, with degradation on longer horizons as softmax attention probabilities converge toward uniform importance scores, diminishing the method's ability to identify informative interactions; and (3) temporal attribution patterns in faithful methods reflect genuine task structure rather than recency or popularity bias.

Akash Pandey, Kanisha Shah, Addrish Roy +5

Capital One, AI Foundations San Jose, CA, USA · Capital One, AI Foundations New York, NY, USA · Capital One, AI Foundations McLean, VA, USA +1

Gradient-Based Attribution Sequential Recommendation Temporal Credit Assignment Attention Mechanisms Explainability Evaluation Explainable Recommendation

Sep 23, 2026cs.CV

Diverse by Design: Architectural Constraints for Prototype-Based Interpretability

Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes converge to redundant features, fail to capture diverse semantic parts, and lack quantitative interpretability assessment. We propose Diversity-Aware Prototype Learning (DAPL), which enforces prototype diversity through architectural constraints rather than explicit regularization. Our approach leverages multi-head self-attention with strict one-to-one attention-to-prototype mapping, ensuring each prototype specializes in distinct visual features. We further introduce foreground-aware training to focus prototypes on semantically meaningful regions and develop comprehensive evaluation metrics (Coverage and Diversity) for quantitative interpretability assessment. Experiments on CUB-200-2011 demonstrate substantial improvements: DAPL with foreground-aware training achieves 81.69% accuracy with 0.596 Coverage and 0.427 Diversity, providing the best overall balance across all evaluated prototype-based methods. Code is available at https://github.com/xinmiaolin/DAPL.

Xinmiao Lin, Matthew Wright

Rochester Institute of Technology

Prototype-Based Classification Prototype Learning Explainable Image Classification Explainability Evaluation

Sep 22, 2026cs.CV

MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Models

Visual attribution methods typically explain predictions using pixels, superpixels, or regular patches. These representations can localize important regions, but provide limited information about their structure. We introduce MorphoSHAP, a model-agnostic post-hoc method that instead uses morphological shapes as the players of a Shapley attribution game. Using the Tree of Shapes, each shape is described by its scale, geometry, and signed contribution, providing explanations of where the evidence lies, what type of structure carries it, and how strongly it affects the prediction. This shared morphological vocabulary enables spatial, textual, and global class-level explanations beyond image-specific heatmaps. To the best of our knowledge, MorphoSHAP is the first SHAP-based image attribution framework to combine these different forms of explanation. Across five diverse datasets and three architectures, MorphoSHAP achieves strong insertion/deletion performance and outperforms competing attribution methods on several benchmarks. Finally, a user study shows that MorphoSHAP provides explanations that are easy to use and are preferred over standard attribution baselines.

Anirudh Prabhakaran, Alexandre Rocchi, Gianni Franchi

AMIAD, Pˆole Recherche, Palaiseau

Feature Attribution SHAP Feature Attribution Explainable Image Classification Explainability Evaluation

Sep 20, 2026cs.CV

Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability

Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical in safety-critical domains such as autonomous driving and medicine. This study investigates whether Knowledge Distillation transfers the spatial feature attribution of a large teacher network to a compact student. To assess the influence of the KD scheme on interpretability, we distill a ResNet-152 teacher into a ResNet-34 student on ImageNet-1K across five configurations by systematically varying the distillation temperature and soft-label loss weight. Models are evaluated on top-1 accuracy, along with two interpretability metrics: Relevance Mass Accuracy and Relevance Rank Accuracy. These metrics are computed via Grad-CAM heatmaps benchmarked against ground-truth object masks. Our results show that top-1 accuracy ranges from 71.6% to 74.0%. For Grad-CAM, RMA ranges from 7.7% to 9.7% and RRA from 7.3% to 10.1%; for Guided Grad-CAM, RMA ranges from 16.1% to 18.6% and RRA from 15.9% to 21.5%. Interpretability proves far more sensitive to the soft-label weight than to the temperature: keeping the student anchored to hard labels preserves both accuracy and coarse localization, whereas weighting the teacher heavily degrades both. Fine-grained attribution, however, fell below the undistilled baseline in every configuration tested, indicating that logit distillation transmits where a model attends more readily than the pixel-level structure of that attention. We evaluate 12 cross-architecture combinations of convolutional and transformer-based models, revealing that the inheritance of fine-grained spatial reasoning is fundamentally bottlenecked by the student's intrinsic structural biases. To our knowledge, this is the first application of this interpretability-aware evaluation framework - previously used for neural network pruning - to KD.

Aleks Czufarow, Ihor Babin

XIV High School of Stanislaw Staszic,Warsaw,Poland · Ukrainian Catholic University, Lviv, Ukraine

Neural Network Interpretability Cross-Architecture Knowledge Distillation Explainability Evaluation

Sep 17, 2026cs.CV

When Do Language-Grounded Explanations Help? A Graph-Bottleneck for Farm Monitoring Interpretable Sheep Facial Pain

Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockperson cannot act on a score that arrives without justification. We ground a model in the Sheep Pain Facial Expression Scale (SPFES) by letting each detected facial region attend over text embeddings of the clinical descriptors and then test whether the resulting explanations mean anything. They do not. Ablating an entire descriptor changes the predicted logit by about

10^{-4}

, and the most-attended cue agrees with the predicted pain level in only

32.6\%

of regions, although the attention maps, the learned gate, and the generated text all proposed otherwise. We therefore remove the appearance bypass with a concept bottleneck whose classifier reads only SPFES concept scores, supervised by per-region state annotations that image-level pipelines discard. This costs

0.05

--

0.10

in Cohen's

κ

but yields concepts that are demonstrably learned: minority pain-indicating states are recovered at

3.5

--

8.3\times

their base rates, and the ear and eye severity orderings emerge without severity supervision. Removing the supervision alone leaves

κ

unchanged while concept accuracy falls to

0.109

, showing that architectural necessity does not imply semantic validity. We also show that pooled concept accuracy is misleading under clinical imbalance and provide a cross-validated, protocol-matched benchmark of seven methods on this dataset.

Alam Noor, Miguel Guti'errez Gait'an

CISTER Research Center, Porto, Portugal. · Department of Electrical Engineering, Pontificia Universidad Cat´olica de Chile, Santiago 7820436, Chile.

Concept Bottleneck Models Facial Expression Recognition Explainability Evaluation

Sep 17, 2026cs.LG

Evaluating Explanation Methods by the Predictors They Induce

Explanations of machine learning models are usually judged by criteria that are hard to compare. We propose a simpler test: if an explanation really describes how a model uses its features, it should be possible to rebuild the model's predictions from it. We turn each explanation into a predictor by reading each feature's effect and adding them up, and measure how well that predictor reproduces the model on unseen data. Nothing is fitted, so the score reflects the explanation itself. The test applies to any explanation that can be written as a function of the features; we demonstrate it on partial dependence plots (PDP), accumulated local effects (ALE), SHAP and LIME. We prove that summing partial dependence curves gives the best possible additive summary of a model when its features are independent, and that this fails when they are dependent. Across 13 real datasets and 9 synthetic designs and four model families, which method scores best depends entirely on feature dependence: where features are independent SHAP is slightly worse than PDP, exactly as the theory predicts; on dependent real data SHAP leads. Some widely used quality metrics even prefer a damaged explanation to an intact one.

Jacob Selbæk, Hugo L. Hammer

Department of Computer Science, Oslo Metropolitan University, Oslo, Norway · Department of Holistic Systems, SimulaMet, Oslo, Norway · Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway

Feature Attribution SHAP Feature Attribution Explainability Evaluation Explanation Evaluation

Sep 16, 2026cs.AI

TRIPROBE: Probing Task Separability Beyond Classification for XAI

Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.

Amirhossein Sadough, Freek Hens, Aleksa Bokšan +2

Machine Learning and Neural Computing Radboud University Nijmegen, Netherlands · Delft University of Technology Delft, Netherlands · Unconventional Computing Lab University of the West of England (UWE) Bristol, United Kingdom

Multi-Task Learning Representation Probing Explainability Evaluation

Sep 15, 2026cs.NI

Beyond Measurement Metrics: A Human-Centered Framework for Semantic Validation of Network Traffic Classification

Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a model is only valuable if it learns semantically meaningful and trustworthy patterns rather than exploiting spurious correlations. Conventional evaluation practices predominantly assess predictive performance. Consequently, whether the model relies on semantically meaningful patterns remains unknown. To address these challenges, we adapt the knowledge generation framework for network traffic classification. The adapted framework combines data, ML models, explainability, visualization, and expert reasoning to support the iterative exploration, verification, and refinement of model behavior and data preprocessing. The framework is grounded in findings from the literature, benchmark dataset analyses, practical experience with XAI-based traffic classification, and expert feedback, providing practical guidance for semantic model validation. By complementing predictive performance with semantic validation and human expertise, the proposed framework supports the development of network traffic classification models that are not only accurate but also robust and trustworthy.

Igor Cherepanov, David Sessler, Alex Ulmer +2

Fraunhofer IGD, Darmstadt, 64283, Germany. · Technische Universität Darmstadt, Darmstadt, 64289, Germany.

Human-in-the-Loop Evaluation Explainability Evaluation

Sep 14, 2026cs.AI

Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details

AI-driven automated decision-making requires both predictive performance and interpretability. Recent advances in interpretable machine learning (IML) provide tools for explaining model predictions, but the technical complexity of these explanations may hinder accessibility to non-experts. To address this challenge, this study integrates data storytelling with IML to enhance the explainability of AI-generated decisions for a broader audience. Following the design science research (DSR) paradigm, this study proposes a formal definition of data storytelling in IML, introduces the DIST Pyramid to align data storytelling with IML, and presents the I-P-O Model to describe their interactions. It further develops an architecture to explain AI decisions through distinct "What-if" and "Why-not" event-generation processes. The architecture also employs data desensitization to protect sensitive input data. To validate the approach, a case study is conducted with the Boston Housing dataset, using SHapley Additive exPlanations (SHAP) values and large language models (LLMs) to generate data stories with And-But-Therefore (ABT) structures. An empirical evaluation shows that 76.4% and 74.3% of respondents rated the "What-if" and "Why-not" data stories as more comprehensible, with significantly higher accessibility scores than traditional SHAP visualizations. The paper concludes with the presentation of a narrative interpretation framework that integrates IML and data storytelling, thereby expanding the research scope as well as the practical applicability of AI decision-making.

Lemen Chao, Zixuan Yang, Anran Fang +2

a Key Laboratory of Data Engineering and Knowledge Engineering, Ministry of Education, Renmin University of China · b School of Information Resource Management, Renmin University of China

Interpretable ML Explainability Evaluation

Sep 14, 2026cs.AI

EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models

EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limits clinical trust and neuroscientific validation. We propose a unified attribution framework for interpreting EEG foundation models across heterogeneous architectures. The framework integrates gradient-, perturbation-, and activation-based explanation methods to analyze model behavior in spatial, temporal, and frequency dimensions. Spatially, it identifies critical EEG channels and visualizes their distributions using topographic maps. Temporally, it highlights decision-relevant signal segments through attribution heatmaps. In the frequency domain, it quantifies the contributions of canonical EEG rhythms via spectral perturbation analysis. To assess explanation reliability, we introduce a population-level evaluation combining Area Over the Perturbation Curve (AOPC) and cross-method consistency analysis. The framework further leverages Large Language Models (LLMs) to transform structured attribution outputs into natural-language reports, bridging low-level neural representations and high-level semantic reasoning. Experiments on benchmark datasets, including Mumtaz2016 and TUAB, demonstrate that the generated explanations are consistent with established neurophysiological markers, validating meaningful neural representations while exposing potential dependencies on artifacts and spurious patterns. The proposed framework provides a standardized approach for evaluating the interpretability, reliability, and physiological plausibility of EEG foundation models.

Hansong Ma, Junxiao Wang

Guangzhou University, China

Gradient-Based Attribution Perturbation-Based Feature Attribution Explainability Evaluation EEG Foundation Models

Sep 13, 2026cs.LG

Calibrating Interpretability Instruments Before Trusting Their Verdicts

Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an interchange patch among others. These measurements fail in specific, diagnosable ways that return a plausible number instead of an error, so a broken instrument can easily read as a finding. A covariance-matched null can saturate until every direction looks typical, a per-head attribution can overshoot the true residual write threefold on reordered-normalization architectures, an interchange patch can go sign-chaotic because its outcome is pinned at a ceiling, or a read-from verdict can be an artifact of measuring past the layer where the model already decided. This note documents six such failures from a causal interpretability program on refusal and moral representation, spanning several papers and a four-model open-weight panel; each mode is established on one or two of the four. For each we give the tell that catches it and a protocol keyed to a detectable trigger (reordered normalization, massive activations, a low-dimensional decision channel), so we and readers can check whether a given setup is exposed. The discipline reduces to four moves: calibrate against a positive-control ladder, certify with an orthogonal cell, compute power before spending compute, and state every read-from verdict at a depth referenced to the model's commitment. The evidence is four architectures across three families within a single program; external replication across programs is future work.

Orion Reblitz-Richardson

Distiller Labs

LLM Interpretability Causal Interpretability Causal Interventions in Language Models Explainability Evaluation

Sep 12, 2026cs.AI

LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study

Genetic Programming and its variants, such as grammatical evolution, are widely used in Symbolic Regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be complex or scientifically inconsistent. In this study, we explore whether Large Language Models, can assist in improving the explainability of Symbolic Regression models generated by evolutionary computation methods. Building upon our previous work on estimating body fat percentage using grammar-based Genetic Programming , we investigate the use of LLMs as post-processing tools to analyze and rank evolved expressions according to their interpretability and medical plausibility. Four symbolic expressions are analysed by three LLMs over three repeated runs, and the resulting interpretations and rankings are assessed by a panel of three clinicians. Across the three LLMs, comparative model-ranking outputs received more favorable clinician assessments than isolated term-level interpretations. However, the LLMs also produced physiologically and mathematically questionable explanations, indicating that they are better suited to comparative auditing under expert oversight than to autonomous validation.\blfootnote{The present work is an extended version of a paper submitted into a journal.

Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz +6

Computer Architecture Department, Universidad Complutense de Madrid, Spain. · Bioinspired Intelligence Ltd., Pozuelo de Alarc´on, Spain · Universidad Aut´onoma de Baja California, M´exico +7

LLM Auditing Explainability Evaluation Symbolic Regression

Sep 10, 2026cs.AI

XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?

Evaluating the quality of explanations produced by explainable AI (XAI) methods remains challenging because existing approaches often rely on subjective human judgment, limiting reproducibility, scalability, and comparability between studies. We examine whether LLMs can serve as a reproducible and scalable mechanism to make comparative assessments of the quality of XAI explanations. We introduce XAI-Arena, an LLM-as-a-judge framework for scalable, reproducible, multidimensional, and stakeholder-sensitive evaluation of XAI explanation quality. XAI-Arena then allows us to compare XAI explanations along various dimensions, namely, perceived simplicity, clarity, task adequacy, trust calibration, actionability, transparency, faithfulness, and overall interpretability. We then benchmark XAI explanation methods across various datasets, machine learning models, and stakeholder personas. Human validation shows a strong positive association between LLM-generated and human ratings (Spearman's rho=.693, p<.001). Together, LLM-based evaluations can capture systematic differences in XAI explanation quality and provide a scalable and reproducible framework for comparative assessment of XAI explanations.

Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +1

LMU Munich, Germany · Chair of Information Systems, School of Business and Economics, Humboldt-Universität zu Berlin, Germany · Scientific Computing Center, Karlsruhe Institute of Technology, Germany +1

Explainable Artificial Intelligence LLM-as-a-Judge Explainability Evaluation Explanation Evaluation

Sep 8, 2026cs.LG

XAI-Refine: An Automated Explanation-Knowledge Loop for Brain-Age Prediction

Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reproducible or neurobiologically supported mechanisms. Post-hoc explanation methods can expose these mechanisms, but existing workflows typically stop at diagnosis or require correction targets to be specified before model analysis. We propose XAI-Refine, an automated explanation-knowledge loop for brain-age prediction from resting-state functional connectivity. At each iteration, XAI-Refine consolidates complementary post-hoc analyses across repeated training runs into reliable, structured model explanations. It converts each reliable explanation into a neutral neurobiological question, retrieves and verifies relevant literature, and compiles the verified evidence into an admissible set in the same typed explanation space. The target for refinement is defined as the minimal projection of the current model explanation onto the admissible set induced by applicable verified knowledge. This revised explanation is then translated into a differentiable constraint while preserving the originating model variable, measurement operator, and applicable scope. Candidate updates are promoted only when multi-seed validation confirms target-directed explanatory movement, predictive performance remains within a prespecified guardrail, and non-target explanatory drift remains bounded. Experiments on functional-connectivity-based brain-age prediction evaluate predictive performance, explanation reliability, literature alignment, and target-specific model revision, illustrating a structured route from post-hoc analysis to evidence-guided model refinement.

Yang Qiao, Junjie Wu, Deqiang Qiu +2

Department of Computer Science Emory University Atlanta, Georgia, USA · Department of Radiology and Imaging Sciences Computational NeuroImaging & Neuroscience Lab, Emory University Atlanta, Georgia, USA · Department of Neurology Emory University School of Medicine Atlanta, Georgia, USA

Explainable Artificial Intelligence Functional Connectivity Brain Age Prediction Neuroimaging Explainability Evaluation

Sep 8, 2026cs.LG

Do Reasoning Representations Help Humans Evaluate LLM Outputs?

Reasoning representations are increasingly used as explanations for large language model outputs. Yet they are typically evaluated with model-centric criteria, such as answer accuracy and faithfulness, leaving it unclear whether they help people evaluate model responses. In this work, we study reasoning representations as human-facing interfaces rather than proxies for model reasoning ability. We conduct a controlled human study of six reasoning formats across tasks of varying complexity, supported by a web-based framework that randomizes task domains, problem instances, and representation order. The study collects fine-grained judgments of structural understanding, error detection and localization, and trust calibration. Our study shows a mismatch between perceived preference and support for human evaluation. Participants prefer planning- and decomposition-based representations, but simpler chain-of-thought traces better support verification, trust, and interpretability. Preferred representations also introduce calibration risks, with more false alarms on correct traces and high trust despite low willingness to verify.

Jaewoo Lim, Sungbok Shin, Sanghyun Hong

Oregon State University, Corvallis USA · Sogang University, Seoul, South Korea

LLM Evaluation LLM Interpretability CoT Reasoning Human-in-the-Loop Evaluation Explainability Evaluation

Sep 7, 2026cs.CV

A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation

Deep learning has achieved state-of-the-art performance in echocardiographic video segmentation, with an increasing number of models incorporating temporal information. However, quantitative evaluation of temporal explainability remains largely unexplored. We propose a quantitative framework for evaluating Grad-CAM explanations using four complementary metrics measuring temporal consistency, saliency motion, anatomical overlap, and temporal overlap. Using EchoNet-Dynamic, we compare a baseline 2D U-Net with ConvLSTM U-Net models trained across multiple temporal strides. While segmentation performance remained comparable across all models, intermediate ConvLSTM explanations exhibited substantially lower saliency consistency and greater centroid motion than final prediction explanations. Temporal Bottleneck explanations were significantly more stable than Encoder Bottleneck explanations across all strides, while final ConvLSTM Decoder3 explanations were broadly comparable to those of the 2D U-Net. Importantly, conventional frame-wise explanation metrics cannot determine whether variation in intermediate explanations reflects meaningful temporal feature evolution or explanation instability. These findings establish a preliminary quantitative framework for temporal explainability and motivate temporal-aware XAI methods that explicitly account for evolving representations in medical video models.

Jiyoo Noh, Jonathan H. Chan

University of Toronto, Canada · King Mongkut’s University of Technology Thonburi, Thailand

Ultrasound Image Segmentation Explainability Evaluation

Sep 7, 2026cs.AI

Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model pruning. Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity levels up to 95%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability.

Nazish Khalid, Tausifa Jan Saleem, Amal Saqib +2

Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409 USA · Computing and Mathematical Sciences Division, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Model Compression Explainable Medical Image Analysis Explainability Evaluation Neural Network Pruning

Sep 7, 2026cs.AI

Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective

We observe a phenomenon that current algorithmic research in the field of explainable artificial intelligence primarily pursues better performance on several proxy metrics. On the one hand, these proxy metrics themselves are more or less flawed and cannot properly measure the quality of methods. On the other hand, metric-oriented research approaches often lead to the neglect of the rationality and interpretability of the methods themselves. Explainable artificial intelligence is abbreviated as XAI. The metric-driven research paradigm has resulted in a lack of interpretability of the relevant XAI methods themselves. Accordingly, there is a need for interpretability research on XAI methods, which can be playfully referred to as XXAI. This paper is one of our works on XXAI. This paper takes Generic Attention-model Explainability (GAE), a widely influential model interpretation method , or rather, XAI method that represents an important technical route, as the research object, and explores the real working mechanism and flaws of this method as well as the technical route it represents. Based on the conclusions of this study, it may be necessary to re-examine or verify GAE-related methods and their domain applications. We argue that GAE is an interpretation method that focuses on the attention process. After pointing out the working mechanism and flaws of GAE, we propose Cumulative Asset Holdings (CAH), a more reasonable Transformer interpretation method integrating both process-based and feature-based ideas from an economic zero-sum games perspective. In addition, it is worth noting that our method is applicable to models with special tokens, where existing methods may suffer from limitations. The model simplification research method and the analysis of additive operations adopted in this study may provide inspiration for other research works in XAI.

Yongjin Cui, Xiaohui Fan

Zhejiang University

Transformer Interpretability Explainable Artificial Intelligence Explainability Evaluation

Sep 4, 2026cs.AI

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a system, diagnose errors, or decide when to escalate an output. Such use assumes that the explanations agree with the component's observable decision behaviour. We test two interpretations of the named factors: necessity, meaning that changing a factor would change the output, and sufficiency, meaning that retaining it while removing other changeable information would preserve the output. We evaluate these interpretations in two synthetic use cases: recommending advisors to clients and judging prompts for harmfulness or risk. Models return an output and the top three factors that most influenced it. Controlled black-box interventions estimate a necessity score for each factor by measuring how often changing it changes the output, and a sufficiency score by measuring how often retaining it preserves the output. Across eight models from the Claude, GPT, and Gemini families, the mean Spearman correlations between the cited ranking and the necessity and sufficiency scores are 0.349 and 0.354 for advisor recommendation, and 0.431 and 0.580 for prompt monitoring. Furthermore, an uncited factor scores above the lowest-scoring cited factor in 57.6% of advisor responses under necessity and 58.1% under sufficiency; the corresponding prompt-monitoring rates are 25.8% and 8.9%. The cited top three contain useful information but do not reliably identify the three factors with the strongest measured influence under necessity or sufficiency. The framework provides a black-box reliability check for explanations used in agent oversight while remaining scoped to individual LLM decisions.

Urja Pawar, Rajitha Ramanayake, Nabeel Kemal +6

BNY

Faithfulness of Language Model Explanations LLM Auditing LLM Interpretability LLM Decision-Making Explainability Evaluation

Sep 3, 2026cs.CV

Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography

Background. Remote photoplethysmography estimates the cardiovascular pulse from facial video, and its explanations have rested on inspecting heatmaps rather than on quantitative evidence about where a model reads it. We quantified the explanations and asked whether such explanations transfer between datasets and track model performance. Method. We trained eight condition-specific RhythmFormer models on NCKU-rPPG, recorded under three illumination levels, speaking, rotation, and cycling, estimated one heart rate per 5.12-second clip, and set them beside a UBFC-rPPG reproduction. Raw attention, rollout, attention flow, and Beyond Intuition were assessed by skin coverage and the Salience-guided Faithfulness Coefficient (SaCo). Results. Beyond Intuition ranked highest on both datasets, at median coverage 0.789 and SaCo 0.837 on Static level 3 against 0.826 and 0.917 on UBFC-rPPG; lower ranks differed. Within one participant of one condition, neither measure was related to a clip's heart-rate error, waveform correlation, or signal-to-noise ratio on either dataset: 186 of the 252 coefficients fell below

|ρ|=0.10

and 28 reached

p<0.05

against the 13 expected by chance. Across the eight scenarios only Beyond Intuition's coverage followed the three performance measures, at

ρ=-0.43

,

+0.57

, and

+0.43

, while the attention-only methods' SaCo ran opposite to each. It failed at 40 lux alone, its median coverage falling to 0.180 and its median SaCo to

-0.178

, whereas motion degraded the estimates far more without such a drop. Conclusions. Skin coverage and SaCo carry information complementary to the performance measures rather than a proxy for them: attributing to the skin does not guarantee an accurate estimate. What an attribution reveals about a condition is where the model looks rather than how faithfully its map is ordered.

Louis Chen, Torbjörn E. M. Nordling

Department of Mechanical Engineering, National Cheng Kung University, Tainan, Taiwan.

Remote Photoplethysmography Feature Attribution Heart Rate Estimation Explainability Evaluation