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

Jul 23, 2026cs.LO

Explainability Framework for Policy-Aware Autonomous Agents

In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal. As these systems grow more prevalent in our day-to-day lives, there has been an increased need to add explainability features which can provide an account for an agent's behavior. We therefore propose a framework that outlines how to produce comprehensible explanations for policy-aware agents, or agents which have rule-enforcing policies incorporated in their decision-making framework. This framework is designed using insights from the social sciences on how to produce good explanations. It is implemented in the Answer Set Programming language while using Python to assist with information extraction and natural-language translation. Because these agents incur penalties when violating policies, we are able to leverage these penalties to detect undesirable events in scenarios that are counterfactual to the agents' original actions. This lends itself to creating contrastive explanations (e.g., "the agent performed this action because, had it not, undesirable event X would have occurred."), which formulate the core component for our explainability framework. The framework is evaluated using a survey wherein human participants provide feedback on our program-generated explanations.

Heather Merhout, Daniela Inclezan

Miami University · Miami University Oxford, Ohio, United States

Explainable Artificial Intelligence Counterfactual Explanations Explainability Evaluation

Jul 23, 2026cs.LG

Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification

Automated detection of vision impairing retina-based ocular conditions from fundus images is important for early screening, timely referral and reducing dependency on specialist-only assessment, for which neural network-based deep learning (DL) models have been widely utilized. However, explainability of the DL frameworks remains a major bottleneck for clinical adoption, particularly when model decisions are not linked to retinal regions that are clinically meaningful. To address this issue, this study presents CounterFundus, a novel CycleGAN-driven counterfactual explainability framework, integrating EfficientNet-B5-based retinal disease detection with visually interpretable disease-to-normal fundus image translation. For each pathological image, the counterfactual yielded by the CycleGAN generator represents an estimated healthy counterpart and the resultant difference map is utilized to localize disease-associated retinal changes. Unlike conventional post-hoc saliency methods, CounterFundus provides counterfactual explanations through visually plausible disease-to-normal retinal translation. Thereafter, to quantify the spatial agreement between counterfactual difference maps and classifier saliency, the Counterfactual-Classifier Alignment Score (CCAS) is introduced, embedding Spearman correlation, binary IoU and pointing accuracy into a single assessment protocol. To this end, EigenCAM-aligned evaluation demonstrates that the generated counterfactual explanations remain spatially consistent with classifier-relevant retinal evidence across all CCAS dimensions. Along with that, ablation studies further confirm that CCAS-filtered counterfactual augmentation improves the downstream classification performance in fundus images, establishing CounterFundus as a clinically-grounded, explainable artificially intelligence (XAI) framework for retinal disease detection.

Kritanu Chattopadhyay, Sayanjit Singha Roy, Soumya Chatterjee

Department of Mechanical Engineering, National Institute of Technology Durgapur, West Bengal, 713209, India · Department of Electrical Engineering, IIT Kanpur, Uttar Pradesh, 208016, India · Department of Electrical Engineering, National Institute of Technology Durgapur, West Bengal, 713209, India

Counterfactual Explanations Medical Image Classification Fundus Imaging Explainable Medical Image Analysis Counterfactual Data Augmentation Explainability Evaluation

Jul 23, 2026cs.CV

Explainable Deepfake Detection Challenge

Deepfake detection is moving beyond binary classification decisions toward systems that can also explain the visual evidence supporting those decisions. This transition is important for real-world verification settings, where diverse users need to understand not only whether an image is manipulated, but also why it is considered suspicious. The Explainable Deepfake Detection Challenge at ACM Multimedia 2026 is designed to benchmark this joint capability. Built on XPlainVerse, a million-scale benchmark for explainable deepfake detection, the challenge evaluates methods on image classification and grounded natural-language explanation generation. Participants submit a real/fake label together with two explanations for each image: a detailed complex explanation for technical users and a concise simple explanation for general users. The evaluation combines classification metrics with semantic similarity, simplicity, and intent-aware grounding metrics that assess whether explanations identify the relevant manipulated entities and supporting visual evidence. The methodologies developed through the challenge will contribute to the development of next-generation explainable deepfake detectors. Evaluation script, baseline models, and accompanying code are available on https://github.com/Abhijeet8901/XPlainVerse-ACMChallenge.

Abhijeet Narang, Kartik Kuckreja, Shreya Ghosh +4

American University of Sharjah Sharjah, United Arab Emirates

Image Forgery Detection Explainable Deepfake Detection Deepfake Detection Explainable Image Classification Evidence-Grounded Generation Explainability Evaluation

Jul 22, 2026cs.CL

A Multi-Dimensional Evaluation of Explainability in Media Bias Detection

Detecting media bias automatically is difficult because biased framing is often subtle, yet in domains such as news analysis, accurate predictions alone are insufficient without explanations that reflect the model's underlying reasoning. We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias Annotations By Experts (BABE) dataset. Specifically, we study BERT and RoBERTa as classifiers (base and large variants) along three complementary axes: predictive performance, explanation plausibility (token-level alignment with expert rationales), and mechanistic faithfulness (whether compact sets of attention heads recover predictive signal under counterfactual rationale masking). To induce variation in plausibility, we additionally investigate attention-supervised finetuning, which incorporates expert rationale annotations as an auxiliary training signal. Attention supervision serves as an intervention on attribution plausibility, while the effectiveness of attribution methods varies substantially across architectures. Circuit analysis further reveals substantial variation in mechanistic recoverability across architectures, suggesting that model scale alone does not determine circuit compressibility. Taken together, our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior and should be evaluated separately when studying explainability in media bias detection.

Ting Chen, Raina Zhang, Benjamin M. Ampel +1

Carnegie Mellon University · Indiana University · Georgia State University

Attention Head Analysis Mechanistic Interpretability Explainability Evaluation

Jul 21, 2026cs.LG

CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability

Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implementations for discovery, evaluation, and intervention, as well as hand-authoring the contrastive prompts required by many discovery methods. This fragmentation makes methods difficult to compare and limits their application beyond canonical tasks. We introduce CircuitKIT, a source-available library that connects the circuit-analysis workflow through a typed, serializable representation. CircuitKIT provides a suite of discovery algorithms, declarative interfaces for mapping structured data into discovery tasks, complementary circuit diagnostics, and downstream application modules. Together, these components provide common infrastructure for conducting and comparing circuit analyses. The library, examples, notebooks, and documentation are released at https://github.com/Lexsi-Labs/CircuitKIT .

Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1

Lexsi Labs

Circuit Discovery Mechanistic Interpretability Circuits in Language Models Explainability Evaluation

Jul 18, 2026cs.CV

Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model

This position paper argues that claims about explanation stability are scientifically invalid without cross method validation. Just as statistical significance requires the test statistic to be specified, stability should either be evaluated across multiple attribution paradigms or explicitly scoped to the computational objective of a single method. In controlled chest X ray experiments, DenseNet201, ResNet50V2, and InceptionV3 achieved AUC values above 99%, yet their stability rankings reversed across attribution methods. LayerCAM ranked InceptionV3 as the most stable model, with an IoU of 0.777, whereas GradCAM++ favored DenseNet201 and reduced InceptionV3 stability score by 17.3%. These findings demonstrate that explanation stability is an emergent property of the model method pair rather than an intrinsic characteristic of the model alone. We therefore argue that explanation based claims should be validated across multiple attribution methods and that regulatory submissions should explicitly specify the attribution operators used to avoid creating illusory safety assurances.

Kabilan Elangovan, Daniel Ting

Singapore Health Services and Singapore Eye Research Institute, Singapore.

Gradient-Based Attribution Explanation Stability Explainable Medical Image Analysis Explainability Evaluation

Jul 17, 2026cs.CL

From Plausible to Actionable: A Position on LLM Self-Explanations

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior. However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.

Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1

University of Utrecht, Utrecht, Netherlands · National Police Lab AI, Netherlands Police, Driebergen, Netherlands · Scuola Normale Superiore, Pisa, Italy +1

CoT Faithfulness Faithfulness of Language Model Explanations LLM Interpretability Explainability Evaluation

Jul 16, 2026cs.CV

On the Disagreement in Perturbation-based xAI -- Benchmarking Perturbation Choices for Flood Detection from SAR Images

Perturbation-based xAI methods are widely used to analyze the behavior and predictions of deep learning models. By altering input regions and measuring the resulting changes in class probabilities with respect to the original image, they assign relevance scores and generate heatmaps that reflect each region's contribution to the prediction. Despite their apparent simplicity, however, perturbation-based methods are sensitive to parameter choices. In this work, we focus on two key parameters of the perturbation pipeline, namely the patch geometry, including the size and shape of the perturbed regions, and the perturbation type, defined by the replacement scheme. Grounded in the use case of flood detection from Synthetic Aperture Radar imagery, we conduct a comprehensive investigation of how relevance estimation changes under different perturbation settings. Beyond visual inspection of the resulting relevance maps, we evaluate their consistency across perturbation strategies and their faithfulness to the model's reasoning. We demonstrate how different perturbation choices can steer the resulting relevance maps, yielding ambiguous and even contradictory explanations. Our findings emphasize the importance of methodological settings in perturbation-based xAI. They underscore the need to carefully inspect and evaluate perturbation choices and to treat them as an integral part when interpreting explanations, ensuring a robust understanding of both the explanations and model predictions.

Anastasia Schlegel, Ronny Hänsch

Microwaves and Radar Institute, German Aerospace Center (DLR), Weßling, 82234, Germany · Chair of Remote Sensing Technology, Department of Aerospace and Geodesy, Technical University of Munich, Munich, 80333, Germany

Feature Attribution Perturbation-Based Feature Attribution Explainability Evaluation

Jul 15, 2026cs.LG

Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models

In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models, datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source datasets, discussing the implications of the obtained results in relation to the characteristics of the datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems.

Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis +4

Department of Digital Systems University of Piraeus Piraeus, Greece · Department of Business Administration University of Piraeus Piraeus, Greece · Innov-Acts Ltd Innov-Acts Nicosia, Cyprus

Feature Attribution Explainability Evaluation Explanation Evaluation

Jul 15, 2026cs.LG

Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist

Feature-attribution methods are central to explainable artificial intelligence. Their assumptions are expressed in several mathematical languages: cooperative-game values, path integrals, gradient operators, perturbation distributions, and backpropagation rules. This survey proposes a common framework for local additive feature attribution. It organizes Shapley, path-based, gradient/backpropagation, perturbation, and CAM-style methods around five specification choices: value function, reference, path, perturbation distribution, and conservation rule. It then compares these methods through an axiom-by-method matrix and links common failure modes, including baseline sensitivity, off-manifold perturbations, sanity-check failures, adversarial manipulation, and method disagreement, to the assumptions that produce them. Finally, the survey proposes a ten-item reporting checklist for studies that use local additive attributions. The central message is that attribution results are meaningful only relative to the mathematical assumptions under which they are defined, and that those assumptions should be reported.

Rebecca Afriyie Sarpong, Daniel Commey

Gradient-Based Attribution Feature Attribution Perturbation-Based Feature Attribution Shapley Value Attribution Explainability Evaluation

Jul 15, 2026cs.AI

Explaining Reinforcement Learning Agents via Inductive Logic Programming

Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios. However, it is mostly based on user studies, thus targeting the needs of a specific audience and lacking shared evaluation metrics. On the other hand, logic-based approaches within eXplainable Artificial Intelligence (XAI) provide compact, human-readable abstractions of decision-making. However, the systematic quantification of the explainability degree of logical representations remains an open problem. This work aims to advance the state of the art in XRL by introducing objective and planning-oriented metrics for policy explainability in RL settings. At the same time, it contributes to the field of logic for XAI by providing a principled way to quantify the explainability of logical rules, moving beyond common-sense assessments and simple propositional fragments. We employ Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance. These metrics quantify alignment between symbolic rules and agent behavior, the role of features in decision-making, and the evolution of policies during training and across agents in single and multi-agent RL. Experiments across different RL domains show that the proposed metrics highlight action-specific learning dynamics beyond global return, provide fine-grained insights into domain features beyond classical approaches for global feature importance estimation, and uncover coordination, specialization, and adaptation patterns in MARL. Moreover, they provide crucial insights for the transfer and generalization of action-specific policies.

Celeste Veronese, Edoardo Zorzi, Daniele Meli +1

University of Verona, Italy · Sapienza University of Rome, Italy

Interpretability in RL Explainability Evaluation

Jul 12, 2026cs.LG

Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts

Explainable machine learning (XML) pipelines applied to composite mental health outcomes can produce apparently-robust, cross-population-stable risk hierarchies that are largely artefacts of how the outcome was constructed. We demonstrate this using an ElasticNet pipeline applied to 886 medical students at the University of Lausanne (primary cohort, 2022), validated across 2,580 longitudinal observations at three time points and 701 non-medical students from eight faculties; all three datasets share identical instruments. The pipeline produces a hierarchy in which trait anxiety and health satisfaction dominate wherever the outcome is measured, with Kendall

τ= 1.0

for the top-two positions across all five evaluation sets and consistent transfer performance (

R^2

: 0.41-0.49). Two residualization experiments, which isolate shared variance between correlated variables via regression, reveal the mechanism: when trait anxiety (STAI-T) is residualized against the co-included depression subscale (CES-D,

r = 0.72

), model

R^2

drops from 0.41 to 0.16 and STAI-T falls from rank 1 to rank 6; when burnout subscales are residualized against CES-D,

R^2

collapses to 0.016. Prediction intervals average 35.4 units on a 0-100 scale (2.4 outcome standard deviations), independently ruling out individual-level deployment. The residualization protocol is the paper's transferable contribution: any XAI study combining correlated predictor and outcome constructs should apply this check before interpreting apparent stability as a finding.

Alireza Dehghan, Negin Ashrafi

Sharif University of Technology, Tehran, Iran · University of Southern California, California, USA

Explainability Evaluation

Jul 10, 2026cs.AI

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the auditing of human-understandable concept explanations. The framework perturbs input regions, measures concept-response shifts, applies locality weighting, and fits an XGBoost surrogate to approximate local concept behaviour. Reliability is assessed through attribution accuracy, surrogate fidelity, faithfulness, stability, and consistency. We evaluate ConceptSMILE on retinal fundus images by comparing MedSAM-derived visual concepts with VLM-based semantic concepts. Results show that reliability varies across concepts and pathways: MedSAM achieves stronger spatial attribution and the highest surrogate fidelity (

R^2 = 0.8503

,

R_w^2 = 0.8465

), while the VLM pathway shows stronger vessel faithfulness and stronger stability under selected artefact conditions. ConceptSMILE provides an independent audit layer for evaluating the trustworthiness of concept-based XAI.

Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani +3

School of Computer Science University of Hull Hull, United Kingdom · PhD Researcher (Engineering), WMG University of Warwick Coventry, United Kingdom · School of Computing Newcastle University Newcastle upon Tyne, United Kingdom

Concept-Based Explanations Explainable Medical Image Analysis Explainability Evaluation

Jul 9, 2026cs.LG

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one. These experiments are usually summarized by a point estimate, even though the evaluation may be monitored while it runs or adapted toward suspected failures. This makes it hard to tell whether a reported fidelity or patching effect is a stable causal claim or a consequence of finite sampling and evaluation choices. We introduce Certified Interventional Fidelity (CIF), a statistical layer for interventional interpretability evaluations. CIF first writes the quantity being reported as a causal estimand: an expectation of a bounded score over a stated input distribution and a stated intervention distribution. It then provides confidence intervals and anytime-valid confidence sequences for this estimand, including under adaptive intervention sampling via bounded mixture importance weighting. We instantiate CIF with Hoeffding-style sequences and variance-adaptive betting sequences, the latter reducing certification cost by 10-30x in our experiments. On MNIST abstractions and GPT-2 Small IOI circuits, CIF certifies high-fidelity claims, shows when apparent method differences are not statistically supported, and makes sensitivity to the intervention distribution explicit.

Amir Asiaee

Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA

Mechanistic Interpretability Causal Interventions in Language Models Explainability Evaluation Causal Intervention

Jul 8, 2026cs.CV

ReMoDEx: A Local-to-Global Relevance-Based Model Decision Explainability Framework for large-Scale Image Datasets

Deep learning image classifiers achieve strong predictive performance yet remain opaque in how decisions are formed. A model may predict correctly while relying on irrelevant cues, shortcut associations, peripheral structures, or device level artifacts instead of task relevant regions. On large scale datasets this opacity is especially problematic, since inspecting heatmaps one sample at a time cannot scale to thousands of predictions. We propose Relevance Based Model Decision Explainability (ReMoDEx), a framework for systematic, dataset scale assessment of model decision behaviour in image classification. ReMoDEx defines a stepwise pipeline: model inference, target class selection, relevance map generation, heatmap standardisation, similarity based grouping of patterns, cluster level interpretation, and spatial relevance assessment. Local methods GradCAM++, Integrated Gradients, Occlusion Sensitivity, and Layerwise Relevance Propagation are each combined independently with a single global module that summarises an entire set of relevance maps into a few decision strategy clusters, replacing sample by sample inspection with an automatic, scalable summary. To demonstrate ReMoDEx, we applied it to a VGG16 based classifier distinguishing COVID-19, Normal, Lung Opacity, and Viral Pneumonia. The classifier showed stable performance (86.27% test accuracy, 0.9624 test AUC). However, each explainer combined with the global module consistently produced two recurring strategies: central thoracic region decisions and border/corner sensitive decisions, indicating possible shortcut learning that conventional metrics could not reveal. Masked image validation confirmed that model confidence and predicted class changed when central or peripheral regions were occluded. ReMoDEx thus provides a scalable relevance based decision assessment framework and an essential complement to accuracy based evaluation.

Abhay Kumar Pathak, Mrityunjay Chaubey, Manjari Gupta

Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi, India · University of Petroleum and Energy Studies, Dehradun, India

Explainable Artificial Intelligence Explainable Image Classification Explainable Medical Image Analysis Shortcut Learning Explainability Evaluation

Jul 7, 2026cs.LG

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers. Central to our method is an optimization framework that modifies an instance so that the classifier predicts a specified target label, while ensuring that the modification remains easily explainable. The objective function contains two components: an explainability-aware

L_0

(XA-

L_0

) penalty that promotes sparse and interpretable modifications, and a classifier loss objective that steers the perturbed instance toward the desired output. This integrated optimization formulation is used both to identify the underlying causes of misclassification and to evaluate robustness by determining how an instance can change within a tolerance region before being reassigned to another class. To quantify robustness, we introduce the Tolerance Region Confusion Matrix (TOR-Confusion Matrix), which measures a classifier's susceptibility by modeling the class-to-class transition probabilities induced by tolerance-bounded perturbations. We validate the proposed method on both image and tabular datasets, demonstrating its ability to jointly deliver interpretability and robustness assessment.

Evgenii Kuriabov, David Miller, Jia Li

Department of Statistics, The Pennsylvania State University, University Park, PA 16802, USA · Department of Electrical Engineering, The Pennsylvania State University, University Park, PA 16802, USA

Counterfactual Explanations Adversarial Robustness Black-Box Adversarial Attacks Explainability Evaluation

Jul 7, 2026cs.LG

X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models

Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal patient trajectories into generalizable representations for diverse clinical prediction tasks. Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. We train a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while preserving temporal dynamics. We identify the most influential tokens, providing insights into how FEMRs leverage different aspects of patient history for predictions. To evaluate clinical relevance, we introduce a novel clinical alignment metric that quantifies the correspondence between the surrogate model's key tokens and clinically validated features. Our results demonstrate that the surrogate closely approximates FEMR predictions and that token-level explanations align well with clinical knowledge, offering a practical framework for interpretable and trustworthy clinical AI.

Jie Huang, Pengfei Yin, Zihan Xu +3

School of Computing and Information Systems, University of Melbourne, Melbourne, Australia · Department of General Medicine, Royal Melbourne Hospital Melbourne, Australia

Neural Surrogate Modeling Neural Network Interpretability Longitudinal EHR Modeling Explainability Evaluation

Jul 6, 2026cs.LG

Measuring What Matters: A Unified Evaluation Framework for GNN Explainability

Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable. While a growing number of explainers are available, choosing the right method and assessing the trustworthiness of its outputs remains unclear. Consistent evaluation practices and actionable guidance are still missing, hindering practical adoption. In this paper, we introduce a unified, quantitative benchmarking framework for G-XAI that requires no ground-truth assumptions. We formalize tabular explainability metrics for graph data, evaluating topological structure and node features as independent components. Our large-scale benchmarking study identifies explainers that consistently lie on the Pareto front across metric pairs and tasks, establishing robustly non-dominated solutions - while confirming that no single explainer achieves universal superiority. We distill our findings into actionable G-XAI usability guidelines to support Machine Learning practitioners in evaluating and deploying trustworthy GNN-based pipelines.

Francesco Paolo Nerini, Mirko Zaffaroni, Paolo Baracco +2

Sapienza University of Rome, Rome, Italy · Intesa Sanpaolo AI Research, Turin, Italy · Anti Financial Crime Digital Hub, Turin, Italy +1

Explainability Evaluation GNN Explainability

Jul 4, 2026cs.LG

NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution

Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems. Reasoning about such criticality can be formulated as an attribution problem. However, across different decision-making tasks, the causes of criticality may involve diverse state variables, interaction patterns, and failure mechanisms, making attribution an inherently open-ended problem beyond predefined explanation spaces. Existing attribution methods still struggle to balance open-ended reasoning flexibility with the interpretability and traceability required for critical scenario reasoning. To address this limitation, we propose NeSy-CSA, a neuro-symbolic framework that transforms open-ended critical scenario attribution from unconstrained explanation generation into structured and traceable reasoning. NeSy-CSA narrows the attribution space by selecting relevant factors, makes the reasoning process traceable through a dependency-aware evidence graph, and executes symbolic reasoning procedures derived from atomic operations, coordinated with evidence-constrained neural inference to support flexible open-ended attribution. We further introduce a process-level and result-level assessment module to evaluate the structural validity of the attribution process and the behavioral effectiveness of the attribution results under controlled interventions. Experiments across four decision-making environments show that NeSy-CSA improves two intervention-based measures of attribution effectiveness by 18.32% and 13.67% over LLM-based baselines. These results demonstrate its potential to transform discovered critical scenarios into reusable knowledge for subsequent testing and safety analysis.

Qitong Chu, Xunjie He, Chen Deng +2

School of Automation, Beijing Institute of Technology, Beijing 100081, China · Department of Automation, Tsinghua University, Beijing 100084, China

Feature Attribution Neuro-Symbolic Reasoning Explainability Evaluation

Jul 3, 2026cs.CV

XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection

As deepfake detection models increasingly produce natural language explanations, their reasoning often remains weakly grounded in visual artifacts, limiting reliability and user trust. Existing benchmarks mainly evaluate classification accuracy, overlooking whether explanations reflect the actual manipulations. This gap hinders progress toward deployable, explainable deepfake detection systems. To this end, we introduce XPlainVerse, a large-scale benchmark designed for joint deepfake detection and human-centered explanation. XPlainVerse comprises one million real and manipulated images, pairing authentic images from five established sources with forgeries generated by twelve off-the-shelf image editing and synthesis models. We further propose a multi-stage filtering pipeline, Edit-Check, to verify if manipulations satisfy their intended edits, enabling reliable reasoning supervision at scale. Beyond dataset scale, XPlainVerse provides two complementary explanation styles: technical explanations for expert analysis and simplified explanations optimized for non-technical users. To evaluate explanation quality beyond surface similarity, we propose novel metrics, EntityScore and EvidenceScore, that measure reasoning fidelity by checking whether explanations correctly identify manipulated entities and visual evidence. Human annotations on 2,000 explanation pairs validate our dataset quality against human judgment. We believe XPlainVerse will establish grounded explanation quality as a measurable dimension of deepfake detection and support scalable research on trustworthy, interpretable models.

Abhijeet Narang, Kartik Kuckreja, Shreya Ghosh +3

Monash University · MBZUAI · The University of Queensland

Image Forgery Detection Explainable Deepfake Detection Deepfake Detection Explainability Evaluation

Jul 2, 2026cs.CL

AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations

This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk assessment in instructional content for grades K-12. The dataset comprises 1,639 explanations from 170 curated ScienceQA questions, covering science, language arts, and social sciences. For each question, the dataset includes an explanation written by a human teacher alongside 11 explanations generated by LLM-simulated teacher profiles associated with distinct pedagogical risks. We propose a comprehensive risk rubric aligned with established educational standards that covers five complementary dimensions: factual precision, depth and completeness, focus and relevance, student-level appropriateness, and ideological bias. A key contribution is the addition of 785 explanations with structured explainability annotations, including risk localization and risk description. The annotations are produced through a semi-automatic process with expert teacher validation. Finally, we present validation experiments comparing state-of-the-art proprietary models with a lightweight local Llama 3.1 8B model in both the pedagogical risk detection and the explainability assessment. These experiments evaluate whether supervised fine-tuning on AIriskEval-edu-db2 enables a locally deployable model to approach or outperform stronger frontier models while preserving privacy in educational auditing and assessment tasks.

Javier Irigoyen, Roberto Daza, Francisco Jurado +5

BiometricsAI, Universidad Aut´onoma de Madrid (UAM), Spain · GHIA, Universidad Aut´onoma de Madrid (UAM), Spain · Universidad de Las Palmas de Gran Canaria (ULPGC), Spain

LLM Safety Benchmarks LLM Auditing Educational Assessment Generative AI in Education Explainability Evaluation Generative AI Evaluation

Jul 1, 2026cs.IR

Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search

Recommender systems are vital in helping users navigate vast amounts of information, offering personalized suggestions and effective explanations for these recommendations. While previous efforts have attempted to provide such explanations, evaluating their effectiveness across various scenarios remains a challenge. Enhancing these explanations is essential for improving user engagement, trust, and decision-making. To facilitate effective explanations within the recommender system, we propose a Bi-level Neural Architecture Search (Bi-NAS) framework to optimize explanations. This approach simultaneously refines cross-attention mechanisms and feature interaction functions by exploring both intra-layer and inter-layer design spaces. Furthermore, we integrate Large Language Models (LLMs) to enhance explanation generation, leveraging zero-shot prompting to produce more effective and personalized justifications. By aligning user feature preferences with item quality scores, our approach ensures that explanations reflect both user intent and item attributes, improving transparency and reasoning depth. Extensive evaluations on four real-world datasets demonstrate that Bi-NAS not only boosts recommendation accuracy but also significantly improves the effectiveness of explanations for recommender systems, providing users with clear and reliable insights into the suggestions they receive.

Longfeng Wu, Yao Zhou, Tong Zeng +5

Virginia Tech Blacksburg, VA, USA · Google Mountain View, CA, USA · Amazon Sunnyvale, CA, USA

Recommender Systems Neural Architecture Search Explainability Evaluation

Jul 1, 2026cs.LG

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54

\verb|OLMo2-1B|

- and

\verb|gemma-3-1b-it|

-based MOs trained with seven different techniques, including standard post-hoc SFT, post-hoc DPO, and more realistic integration of MO data into the OLMo post-training DPO phase. We use these MO variants to benchmark activation oracles, activation steering, logit lens, and sparse autoencoders. Our findings show that (i) MO interpretability depends strongly on training objective, target behaviour, model architecture, and training data generation pipeline; (ii) substantial variance remains even after controlling for differences in the strength of target behaviour expression; and (iii) our more realistic

\textit{integrated training}

often yields less interpretable MOs than standard post-hoc methods. Our results cast substantial doubt on the validity of current MOs as interpretability proxies.

Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere +2

1LASR Labs

Mechanistic Interpretability Language Model Post-Training Explainability Evaluation

Jul 1, 2026q-fin.CP

Shapley in Context: Explaining Financial Language with Domain Expertise

In recent years, large language models have achieved remarkable success and have seen growing adoption in financial applications. At the same time, explainability remains critical in finance, a domain characterized by high stakes and strict regulatory requirements. Although numerous methods have been proposed to explain black box machine learning models, the majority of these approaches are designed for general purpose tasks and do not incorporate domain specific knowledge. In this work, we study the explainability of financial textual data modeled by large language models through the lens of the Shapley value. Specifically, we investigate whether Shapley based attributions align with established financial domain knowledge. Through rigorous theoretical analysis and extensive empirical evaluations, we demonstrate that Shapley values can yield explanations that are consistent with financial reasoning and can offer meaningful insights into the model's behavior in text based financial applications.

Dangxing Chen, Pengzhan Guo

Zu Chongzhi Center, Duke Kunshan University, Kunshan, Jiangsu, CN · Digital Innovation Research Center, Duke Kunshan University, Kunshan, Jiangsu, CN

LLM Interpretability Shapley Value Attribution Explainability Evaluation

Jun 30, 2026cs.LG

Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact. Their outputs, however, are not easily reusable: selectivity tables, circuit diagrams, and feature lists remain locked in per-study notebooks - non-composable, not queryable in natural language, and not directly actionable for downstream audit or intervention. We study the representation layer that sits between these analyses and downstream use as a bottleneck that can be evaluated independently, and introduce Manifestation Units, a typed tuple protocol (E, S, R, D, G) extended with attention-head primitives (T) for transformer architectures, organising per-component statistics into structured fields populated automatically and queried through hybrid retrieval. Instantiated across generative vision (beta-VAE), discriminative vision (CNN), and language (GPT-2), the protocol supports two findings: typed structure substantially outperforms unstructured baselines on retrieval, and CNN filters retrieved by the schema satisfy causal sufficiency and necessity criteria under matched-budget controls. The schema absorbs attention-head primitives without modification, set-recovers known IOI circuit members under retrieval-budget-matched controls, and reveals an irreducible two-field core (S+R) with remaining fields either redundant or actively interfering. We present this as schema infrastructure for mechanistic interpretability rather than frontier-scale validation.

Hussein Chouman, Wataru Sasaki, Tomokazu Matsui +2

Ubiquitous Computing Systems Laboratory, Nara Institute of Science and Technology, Nara, Japan.

Transformer Interpretability Mechanistic Interpretability Explainability Evaluation

Jun 30, 2026cs.LG

Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?

Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens. This creates a surrogate problem: when do measurements made on open models allow us to make claims about a closed model? We evaluate surrogate fidelity at the prediction, attribution, and representation levels. For binary classification tasks, log-odds provide an API-compatible scalar readout of the model's representation space, and leave-one-out attributions provide insight into model behavior. Across eleven models spanning four families (Llama, Qwen, GPT, and Gemini), we find that prediction fidelity substantially overstates attribution fidelity: models that agree on what the answer is often disagree on why. We document an access-validity inversion: white-box signals like attention patterns and perturbation magnitudes are highly stable across models but only weakly predictive of causal attributions, which black-box input ablations capture by design. Mechanistic insight does not automatically transfer to closed targets, and prediction-level agreement is insufficient to warrant such transfer. Code and results are available at https://github.com/facebookresearch/surrogate.

Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5

1Meta.

Faithfulness of Language Model Explanations LLM Interpretability Mechanistic Interpretability Causal Interpretability Explainability Evaluation

Jun 29, 2026cs.CV

On the Faithfulness of Post-Hoc Concept Bottleneck Models

Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color. To bridge the gap between opaque deep learning representations and human understanding, Post-Hoc Concept Bottleneck Models (post-hoc CBMs) project latent features onto interpretable concept spaces using auxiliary datasets or vision-language models. However, relying on target task accuracy as the primary measure of post-hoc CBM success obscures whether the learned concepts are semantically meaningful or merely predictive artifacts. For example, random concept projections can achieve competitive accuracy despite being semantically meaningless. In this work, we analyze the learned projections directly and identify two failure cases: First, for concept projections learned from auxiliary data, covariate shifts can lead to unfaithful concept representations for the target task. In particular, we provide an upper bound on the error introduced by this shift. Second, systematic label noise in surrogate concept labels generated by vision-language models leads to unfaithful projections. After formalizing these failure modes, we introduce novel metrics that decouple concept faithfulness from predictive accuracy. Our empirical results across real-world and synthetic benchmarks confirm that these metrics identify unfaithful behaviors that standard accuracy-based evaluation fails to detect.

Laines Schmalwasser, Jan Blunk, Niklas Penzel +2

Institute of Data Science, German Aerospace Center, Jena, Germany · Computer Vision Group Jena, Friedrich Schiller University Jena, Germany · GEOMAR Helmholtz Centre for Ocean Research Kiel, Germany

Concept Bottleneck Models Explainability Evaluation

Jun 28, 2026cs.LG

Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?

Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability. This is typically done by assigning semantic roles to individual expert components, for example roles like synergy, redundancy, and uniqueness in multimodal settings. However, whether such structural role decomposition preserves explanation faithfulness of the overall architecture remains largely underexplored. We hypothesize that inter-expert representation overlap weakens effective role separation and degrades attribution-based faithfulness, even when semantic roles are explicitly defined. To address this limitation, we introduce representation-level decorrelation regularization to explicitly reduce inter-expert similarity in latent space. Using representation decorrelation objectives, we encourage clearer specialization among experts by minimizing representation overlap. Our experiments show that across multiple multimodal benchmarks, this separation consistently improves explanation faithfulness, as measured by comprehensiveness, sufficiency, and their Area Over the Perturbation Curve (AOPC) summaries, while preserving task performance. We further show that these improvements are not limited to role-based architectures such as Interpretable Multimodal Interaction-aware MoE (I2MoE). Similar trends are observed in a standard sparse MoE baseline, suggesting that representation-level separation may provide a more general mechanism for enhancing explanation faithfulness in MoE systems. Overall, our findings suggest that structural role decomposition alone may be insufficient to guarantee faithful explanations and that representation-level separation helps improve explanation faithfulness. To support reproducibility, the source code and supplementary material are publicly available at https://github.com/dut0817/FL-I2MoE_Decor.

Yeji Kim, Housam Babiker, Mi-Young Kim +1

University of Alberta, Edmonton, AB, Canada · University of Waikato, Hamilton, New Zealand · University of Alberta, Camrose, AB, Canada

Multimodal Model Interpretability Mixture-of-Experts Models Explainability Evaluation

Jun 28, 2026cs.LG

Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models

Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the phenomenon the model has been trained on. The transition may be taken to be secured once the model is reliable enough and the explanation faithful enough. We argue it is not. Reliability checks that the model's predictions match the phenomenon's outcomes, and faithfulness checks that the explanation matches the model, but neither checks whether the model works as the phenomenon works, which is what a claim about structure requires. The chain can support candidate hypotheses under external corroboration, but it cannot, on its own, support claims about how the phenomenon is in fact structured.

Nick Oh, Helen Jin

socius labs, London, United Kingdom · Department of Computer and Information Science, University of Pennsylvania, Philadelphia, Pennsylvania, United States.

Interpretable ML Scientific ML Explainability Evaluation

Jun 26, 2026cs.LG

What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs

Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs. Yet it remains unclear whether these explanations are sufficient, i.e., if they contain enough information to explain the model's output-generating process. We generalize classical sufficiency from feature attributions to arbitrary explanations and prove that explanation sufficiency can change depending on the input distribution, which must be explicitly defined for LLM explanations. We propose using the LLM itself to generate alternative inputs conditioned on an explanation, capturing its beliefs about possible inputs. We formalize self-consistent sufficiency as a goal for free-text explanations and introduce an information-theoretic metric, SCSuff, that enables evaluation of free-text explanations without relying on predefined biases or shortcuts. Our experiments show that SCSuff agrees with targeted perturbation tests where applicable and demonstrate that explanation sufficiency can vary with the input distribution. We find LLM explanations are generally insufficient and weakly correlated with model size, accuracy, or output entropy. Analysis of final-token hidden states shows that top and bottom SCSuff scores can be predicted from internal representations, suggesting that SCSuff can guide detection and improvement of sufficient LLM explanations. The code for this paper is available at https://github.com/rajesh-lab/self-consistent-sufficiency .

Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath

New York University

LLM Evaluation LLM Interpretability Explainability Evaluation Explanation Evaluation