Overview

Explainability evaluation studies whether an explanation reflects a model’s behavior and whether people can use it to understand, verify, or act on a decision. Common approaches measure faithfulness with feature removal, perturbations, counterfactuals, or causal interventions; assess stability across inputs, models, and data shifts; and compare explanations with ground-truth annotations or domain knowledge. Human studies test comprehension, decision performance, trust, and error detection, while benchmarks increasingly combine these outcomes with computational cost and robustness. No single metric works across tasks: scores can depend on architecture and perturbation choices, and mathematical quality or fluent explanations do not reliably predict human understanding or better decisions.

Latest papers

350 papers24 papers in the last four weeks, down 8% on the four weeks before. 0.2% of all new papers.

Nov 19, 2025

CID: Measuring Feature Importance Through Counterfactual Distributions

Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous methods exist, the lack of a definitive ground truth for comparison highlights the need for alternative, well-founded measures. This paper introduces a novel post-hoc local feature importance method called Counterfactual Importance Distribution (CID). We generate two sets of positive and negative counterfactuals, model their distributions using Kernel Density Estimation, and rank features based on a distributional dissimilarity measure. This measure, grounded in a rigorous mathematical framework, satisfies key properties required to function as a valid metric. We showcase the effectiveness of our method by comparing with well-established local feature importance explainers. Our method not only offers complementary perspectives to existing approaches, but also improves performance on faithfulness metrics (both for comprehensiveness and sufficiency), resulting in more faithful explanations of the system. These results highlight its potential as a valuable tool for model analysis. Link to repository: https://github.com/EddieConti/CID
Nov 15, 2025

Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations

Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically perturbing reasoning chains and manipulating delivery tones. Specifically, we analyze reasoning errors in vision language models (VLMs) and how they impact user trust and the ability to detect errors. Our findings reveal two key effects: (1) users often equate trust with outcome agreement, sustaining reliance even when reasoning is flawed, and (2) the confident tone suppresses error detection while maintaining reliance, showing that delivery styles can override correctness. These results highlight how CoT explanations can simultaneously clarify and mislead, underscoring the need for NLP systems to provide explanations that encourage scrutiny and critical thinking rather than blind trust. All code will be released publicly.
Oct 19, 2025

Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration

Complex systems are increasingly explored through simulation-driven workflows that combine physics-based and empirical models with optimization and analytics. Despite their power, these workflows face two central obstacles: high computational cost from repeated expensive simulator runs, and limited transparency when decisions rely on opaque black-box models. We propose a workflow that addresses both challenges by training lightweight emulators on compact designs of experiments that (i) provide fast, low-latency approximations of expensive simulators, (ii) enable rigorous uncertainty quantification, and (iii) support global and local eXplainable Artificial Intelligence (XAI) analyses. This work formalizes a methodological bridge accommodating continuous, categorical, and integer variables across diverse domains, from engineering design to socio-environmental agent-based models. To validate surrogate explanations and examine how faithfully they reflect simulator behavior, we introduce a comparative methodology incorporating active validation filters, including explanation consistency and aleatoric uncertainty quantification. Furthermore, we provide practical guidelines for coupling experimental designs with emulator training to select architectures that balance computational efficiency with interpretability. We demonstrate the framework across two contrasting paradigms: a deterministic multidisciplinary design simulation of a hybrid-electric aircraft and a stochastic agent-based simulation of urban segregation. Results show that coupling surrogates with XAI enables large-scale exploration in seconds, reveals critical nonlinear interactions, and highlights potential design and policy levers while establishing consistent explanations across architectures.
Oct 2, 2025

Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning

AI reasoning models have exceeded human performance on the ARC-AGI-1 benchmark, but does that mean state-of-the-art models have the underlying competence (humanlike abstract reasoning) that the benchmark was designed to test? Here we investigate the abstraction abilities of AI models using the closely related but simpler ConceptARC benchmark. Our evaluations vary input modality (textual vs. visual), use of external Python tools, and reasoning effort. Beyond output accuracy, we evaluate the natural-language rules that models generate to explain their solutions, enabling us to assess whether models recognize the abstractions that ConceptARC was designed to elicit. We show that the best models' rules are frequently based on less abstract, more domain-specific concepts, capturing intended abstractions considerably less often than humans. In the visual modality, AI models' output accuracy drops sharply; however, our rule-level analysis reveals that a substantial share of their rules capture intended abstractions, even as the models struggle to apply these concepts to generate correct solutions. In short, we show that using performance (accuracy) alone can substantially overestimate AI competence in textual modalities while underestimating it in visual modalities, an illustration of the risk of mistaking performance for competence.
Oct 1, 2025

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI

Perturbation-based explainability methods face criticism due to their reliance on out-of-distribution mutants. This raises doubts about the quality of the explanations. In this paper, we introduce a novel forward pass paradigm, Activation-Deactivation (AD), which obviates the need for perturbation of the input. AD replaces perturbation of input features with switching off parts of the model corresponding to to the intended perturbations. We implement ConvAD, an AD approximation algorithm for CNNs. ConvAD is a drop-in mechanism that can be easily added to any trained CNN and, without any additional training, generates more robust and more transferable explanations. We provide evaluation results across multiple architectures, datasets, methods and perturbation strategies, demonstrating the superior quality of ConvAD compared to the SOTA.
Sep 8, 2025

Explainable Information Processing in Particle Swarm Optimization through Landscape and Search Behavior Analysis

Swarm-based optimization algorithms have demonstrated remarkable success in solving complex problems, yet their widespread adoption remains limited due to poor transparency in how algorithmic components influence performance. This work presents a multi-faceted explainability framework for Particle Swarm Optimization (PSO) through two complementary perspectives: landscape-based and algorithmic explainability. From the landscape-based perspective, we develop a comprehensive characterization framework using Exploratory Landscape Analysis (ELA) to quantify problem difficulty, multimodality, and ruggedness, extracting ELA meta-features, dispersion measures, and information content statistics, while a machine learning approach employing Decision Tree and Random Forest classifiers enables prediction of optimal topology-specific hyperparameter configurations for unseen problems. From the algorithmic explainability perspective, we integrate IOHxplainer for temporal convergence profiling and Search Trajectory Networks (STN) for spatial navigation mapping, proposing three novel STN metrics-Connectivity Density, Fragmentation Score, and Search Efficiency-that enhance visual explainability by quantifying topology-specific search organization and transition effectiveness. Through systematic experimentation across 24 benchmark functions in multiple dimensions with Star, Ring, and Von Neumann topologies, we establish practical guidelines for topology selection and parameter configuration. Our findings uncover the black-box nature of PSO, providing greater transparency and interpretability to swarm intelligence systems. The source code is available at https://github.com/GitNitin02/ioh_pso.
Aug 31, 2025

Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy

Active learning is a general learning mechanism shared by artificial and human learners. Whether AI can teach humans such a strategy that transfers across domains is an open question. Ultra Strong Machine Learning (USML), a system whose explanations quantifiably improve human out-of-sample performance compared to self-learning, is uniquely positioned to answer this question. Prior USML work relied on hand-crafted explanation templates that require expert effort for each new domain and do not scale. We developed an explanation pipeline combining Inductive Logic Programming (ILP) with large language models (LLMs) to automate explanation generation and scoring. We tested whether these explanations achieve USML in a human trial teaching active learning strategies across three related domains. Our exploratory results show that concise, expert-written explanations benefit learners with higher initial performance, while pipeline-generated explanations provide no advantage over self-learning despite being rated as higher quality from an LLM-as-judge evaluation. This case study reveals a systematic gap that LLM quality metrics do not predict human learning outcomes. Our findings point to explanation complexity relative to task difficulty as a key factor, and call for explanation methods and evaluation criteria grounded in human cognitive constraints rather than LLM preference.
Aug 16, 2025

Grad-CAM for Visualizing Attention Regions of PCA and SVM Layers in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are an effective approach for classification tasks, particularly when the training dataset is large. Although CNNs have long been considered a black-box classification method, they can be used as a white-box method through visualization techniques such as Grad-CAM. When the training samples are limited, incorporating a Principal Component Analysis (PCA) layer and/or a Support Vector Machine (SVM) classifier into a CNN can effectively improve the classification performance. However, a conventional Grad-CAM cannot be directly applied to PCA and/or SVM layers. Generating attention regions for PCA and/or SVM layers in CNNs is important to facilitate the development of white-box methods. Therefore, we propose PCA-Grad-CAM'', a method for visualizing attention regions in PCA feature vectors, and SVM-Grad-CAM'', a method for visualizing attention regions in an SVM classifier layer. Solving a closed-form Jacobian problem comprising partial derivatives from the last convolutional layer to the PCA and/or SVM layers is necessary to complete the proposed methods analytically. In this paper, we present the exact closed-form Jacobian and visualization results of the proposed methods applied to several major datasets. In addition, the insertion and deletion metrics, which are major evaluation metrics in explainable AI, were applied to PCA- and SVM-Grad-CAM. The results suggest that the proposed method can successfully visualize the attention regions of PCA and SVM.
Aug 14, 2025

Rule2Text: A Framework for Generating and Evaluating Natural Language Explanations of Knowledge Graph Rules

Knowledge graphs (KGs) can be enhanced through rule mining; however, the resulting logical rules are often difficult for humans to interpret due to their inherent complexity and the idiosyncratic labeling conventions of individual KGs. This work presents Rule2Text, a comprehensive framework that leverages large language models (LLMs) to generate natural language explanations for mined logical rules, thereby improving KG accessibility and usability. We conduct extensive experiments using multiple datasets, including Freebase variants (FB-CVT-REV, FB+CVT-REV, and FB15k-237) as well as the ogbl-biokg dataset, with rules mined using AMIE 3.5.1. We systematically evaluate several LLMs across a comprehensive range of prompting strategies, including zero-shot, few-shot, variable type incorporation, and Chain-of-Thought reasoning. To systematically assess models' performance, we conduct a human evaluation of generated explanations on correctness and clarity. To address evaluation scalability, we develop and validate an LLM-as-a-judge framework that demonstrates strong agreement with human evaluators. Leveraging the best-performing model (Gemini 2.0 Flash), LLM judge, and human-in-the-loop feedback, we construct high-quality ground truth datasets, which we use to fine-tune the open-source Zephyr model. Our results demonstrate significant improvements in explanation quality after fine-tuning, with particularly strong gains in the domain-specific dataset. Additionally, we integrate a type inference module to support KGs lacking explicit type information. All code and data are publicly available at https://github.com/idirlab/KGRule2NL.
May 28, 2025

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, current evaluation frameworks for Explainable AI (XAI) in this domain often rely on artificial datasets or simplified tasks, employing data-derived metrics that fail to capture the complexity of real-world scenarios and lack a direct link to explanation faithfulness. To address this, we introduce B-XAIC, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels. Through a comprehensive evaluation using B-XAIC, we reveal limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain. This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.
May 16, 2025

SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite decades of research, most machine learning models for this task are trained on small datasets and still struggle to generalize. Recently, vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities. Their unprecedented generalization capabilities suggest great potential for advancing intelligent robotic surgery. However, surgical VLMs remain under-explored, and existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations and to inform future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind their predictions. This provides a previously underexplored perspective in this field for evaluating the reliability of model predictions. We also propose several explainability analysis-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically relevant visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications.
Apr 23, 2025

Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps

The evaluation of explainable AI (XAI) approaches often relies on three families of methods: subjective measures (e.g., questionnaires on trust or satisfaction), objective measures (e.g., task performance metrics), and mathematical metrics (e.g., for faithfulness). Yet, it remains unclear how these families align or diverge in practice. In a{preregistered} between-subjects study (N=166), we use three established saliency map techniques (LIME, Grad-CAM, Guided Backpropagation) as a testbed to examine this issue. We find that each family of methods leads to different conclusions: participants reported no differences in trust or satisfaction, Grad-CAM improved user performance, while mathematical metrics favored Guided Backpropagation. At the same time, mathematical metrics were only partially related to user performance, and these relationships were sometimes counterintuitive. Our findings highlight the methodological importance of comparing subjective, objective, and mathematical approaches when evaluating XAI, illustrating both tensions and aspects that are aligned. We discuss implications for XAI evaluation frameworks.
Apr 1, 2025

Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

To develop a trustworthy AI system, it is essential to understand its behavior using attribution methods, which aim to identify the input regions that most influence the model's decisions. For discrete inputs such as images, however, accurately identifying input-prediction interactions is particularly challenging because of combinatorial explosion. We formulate black-box attribution as an ordered interpretable subset-selection problem. Inspired by the marginal-gain principle of submodular optimization, the formulation permits redundancy, positive complementarity, and negative interference among input sub-regions. We propose LiMA (Less input is More faithful for Attribution), which ranks sub-regions by their contributions along a sequence of selected subsets. LiMA employs a composite objective that evaluates subsets through semantic consistency, collaboration, prediction confidence, and semantic effectiveness. We further design a bidirectional greedy search to efficiently identify important and non-critical sub-regions. Experiments on eight foundation models (CLIP, ImageBind, LanguageBind, QuiltNet, etc.) and six datasets (ImageNet, VGG-Sound, CUB-200-2011, etc.) demonstrate strong generalization and faithful interpretations with fewer sub-regions. LiMA achieves state-of-the-art Insertion, Deletion, and average highest confidence, with average improvements of 36.3% in Insertion and 39.6% in Deletion; it is also 1.6 times faster than naive greedy search. For failure attribution on incorrect predictions, LiMA improves average highest confidence by 86.1% over state-of-the-art methods. The code is available at https://github.com/RuoyuChen10/LIMA.
Mar 17, 2025

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors actually responsible for the decision? In this work, we analyse counterfactual faithfulness across 75 models from 13 families. We analyze the tradeoff between conciseness and comprehensiveness, how correlational faithfulness metrics assess this tradeoff, and the extent to which metrics can be gamed. This analysis motivates two new metrics: the phi-CCT, a simplified variant of the Correlational Counterfactual Test (CCT) which avoids the need for token probabilities while explaining most of the variance of the original test; and F-AUROC, which eliminates sensitivity to imbalanced intervention distributions and captures a model's ability to produce explanations with different levels of detail. Our findings reveal a clear scaling trend: larger and more capable models are consistently more faithful on all metrics we consider. Our code is available at https://github.com/google-deepmind/corr_faith.
Mar 13, 2025

VisionLogic: Discovering and Grounding Decision-Relevant Visual Concepts

Concept-based explanations help users understand vision models through recognizable visual patterns. However, existing methods often rely on correlational signals without directly validating which image cues support prediction-relevant internal features. To this end, we introduce VisionLogic, a post-hoc framework that grounds these features in visual concepts through intervention-based validation. VisionLogic first identifies compact sets of features whose contributions reproduce the model's original prediction. It then represents their activation states as predicates using class-specific thresholds. An iterative refinement procedure grounds these predicates in visual regions through ablation tests. A region is accepted when its removal deactivates the corresponding predicate, linking the feature's numerical role to visual evidence in the input. The same predicates allow us to examine how features are activated, selected, and reused across images and classes. Across CNNs and vision transformers on ImageNet-1k, we find that only a few features are selected to explain each prediction, and frequently active features are not always selected. In a large-scale human evaluation with 465 participants, VisionLogic significantly improves participants' understanding of model behavior over established methods ACE and CRAFT. Code is available at https://github.com/allengeng123/VisionLogic.
Nov 13, 2024

Causal Explanations for Image Classifiers

Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to find them. However, none of the existing tools use a principled approach based on formal definitions of cause and explanation. In this paper we present a novel black-box approach to computing explanations grounded in the theory of actual causality. We prove relevant theoretical results and present an algorithm for computing approximate explanations based on these definitions. We prove termination of our algorithm and discuss its complexity and the amount of approximation compared to the precise definition. We implemented the framework in a tool ReX and we present experimental results and a comparison with state-of-the-art tools. We demonstrate that ReX is the most efficient black-box tool and produces the smallest explanations, in addition to outperforming other black-box tools on standard quality measures.
Oct 9, 2024

quanda: An Interpretability Toolkit for Training Data Attribution Evaluation

Training data attribution (TDA) methods estimate the influence of individual training samples on a model's predictions, offering a principled lens for interpreting neural networks. Despite rapid methodological progress, TDA evaluation remains scattered across papers and rarely reproducible, making fair comparison between methods challenging. We introduce quanda, a Python toolkit that standardizes TDA evaluation. quanda features a comprehensive collection of evaluation metrics and ready-to-use benchmarks spanning image classification, text classification, and language modeling, alongside a uniform interface for integrating diverse TDA implementations. We showcase quanda through a comparative study of existing TDA methods and find that no approach excels uniformly across metrics, with clear trade-offs between ground-truth faithfulness and downstream task performance. By consolidating the tooling around TDA, quanda equips the community to evaluate attribution methods rigorously and reproducibly. The toolkit is thoroughly tested, documented, and available as an open-source library on PyPI and at https://github.com/dilyabareeva/quanda.
Jun 17, 2024

CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions

Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative features is difficult because real datasets rarely provide reliable ground truth. We introduce a multimodal benchmark containing symbolic tabular, vision, and audio tasks with known informative feature sets. In the main benchmark conditions, informative variables, spatial regions, or channels occupy fixed input coordinates while the remaining inputs provide irrelevant or distracting information. We use the benchmark to study how attribution quality depends on predictive performance, irrelevant-feature burden and structure, model configuration, and attribution mechanism, while separately measuring identification, stability, and computational cost. In most symbolic-data sweeps, informative-set identification co-varies with predictive performance, while the relative ordering of attribution methods remains largely stable. Across modalities, no method dominates all architectures and conditions, and greater attribution complexity does not consistently improve identification. Simple gradient attribution is often competitive at lower computational cost, while the vision and audio results show that architecture and the form of irrelevant content materially affect attribution quality.
Mar 30, 2023

Stop Using Plausibility as the Criterion for Explainable AI

Explainable artificial intelligence (XAI) is motivated by the problem of making AI predictions understandable, transparent, and responsible, as AI becomes increasingly impactful in society and high-stakes domains. The evaluation and optimization criteria of XAI are gatekeepers for XAI algorithms to achieve their expected goals and should withstand rigorous inspection. To improve the scientific rigor of XAI, we conduct the first comprehensive and critical examination of a common XAI criterion: plausibility. Plausibility assesses how convincing the AI explanation is to humans, and is usually quantified by metrics of feature localization or feature correlation. Our examination shows that plausibility is an invalid measure of explainability, and human explanations are not ground truth for XAI, because both ignore the necessary assumptions of explanation. One fundamental assumption is that AI explanations are supposed to behave adversarially, analogous to auditors' or doctors' roles of identifying potential problems. Evaluating or optimizing XAI to generate more plausible explanations is analogous to incentivizing (i.e., bribing) auditors/doctors to generate more positive reports, which is different from encouraging AI models to learn more plausible features (analogous to encouraging companies/patients to improve their conduct/health). Our examination further reveals the consequences of using plausibility as the XAI criterion, including increasing misleading explanations that manipulate users, deteriorating users' trust in the AI system, undermining human autonomy, being unable to achieve complementary human-AI task performance, and abandoning other possible approaches of enhancing understandability. Due to the invalidity of measurements and the unethical issues, this paper argues that the AI community should stop using plausibility as the criterion to evaluate and optimize XAI algorithms.
Nov 16, 2021

Impact of Model Interpretability and Outcome Feedback on Trust in AI

This paper bridges the gap in Human-Computer Interaction (HCI) research by comparatively assessing the effects of interpretability and outcome feedback on user trust and collaborative performance with AI. Through novel pre-registered experiments (N=1,511 total participants) using an interactive prediction task, we analyzed how interpretability and outcome feedback influence users' task performance and trust in AI. The results counter the widespread belief that interpretability drives trust, showing that interpretability led to no robust improvements in trust and that outcome feedback had a significantly greater and more reliable effect. However, both factors had modest effects on participants' task performance. These findings suggest that (1) interpretability may be less effective at increasing trust than factors like outcome feedback, and (2) augmenting human performance via AI systems may not be a simple matter of increasing trust in AI, as increased trust is not always associated with equally sizable performance improvements. Our exploratory analyses further delve into the mechanisms underlying this trust-performance paradox. These findings present an opportunity for research to focus not only on methods for generating interpretations but also on techniques that ensure interpretations impact trust and performance in practice.