Explainable Artificial Intelligence

Also known as XAI

Overview

Explainable artificial intelligence studies how to show why models make particular predictions or take actions, so people can assess errors, bias, uncertainty, and appropriate use. Common approaches include post-hoc feature attribution such as SHAP and LIME, saliency maps for images, counterfactual examples, and models designed around interpretable rules or concepts; newer systems also turn evidence and execution traces into interactive or natural-language explanations. Researchers test whether explanations reflect model behavior and remain stable, but increasingly also measure whether people can understand them and make better decisions in settings such as healthcare, finance, cybersecurity, and autonomous systems. A central tension is that explanations that are faithful to complex models may be difficult to use, while fluent or persuasive explanations can encourage misplaced trust without improving understanding or decisions.

Latest papers

343 papers18 papers in the last four weeks, down 38% on the four weeks before. 0.1% of all new papers.

Dec 7, 2025

TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread ``blind signing'' (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new domain-grounded NLP task for DeFi transaction explanation, and construct a dataset of 187 complex Ethereum transactions with 2,375 token-flow annotations and transaction-level summaries. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions.
Nov 3, 2025

An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations

This work presents a requirement analysis for collaborative dialogues among medical experts and an inquiry dialogue game based on this analysis for incorporating explainability into multiagent system design. The game allows experts with different knowledge bases to collaboratively make recommendations while generating rich traces of the reasoning process through combining explanation-based illocutionary forces in an inquiry dialogue. The dialogue game was implemented as a prototype web-application and evaluated against the specification through a formative user study. The user study confirms that the dialogue game meets the needs for collaboration among medical experts. It also provides insights on the real-life value of dialogue-based communication tools for the medical community.
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 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 28, 2025

On The Variability of Concept Activation Vectors

One of the most pressing challenges in artificial intelligence is to make models more transparent to their users. Recently, explainable artificial intelligence has come up with numerous methods to tackle this challenge. A promising avenue is to use concept-based explanations, that is, high-level concepts instead of plain feature importance scores. Among this class of methods, Concept Activation Vectors (CAVs, Kim et al., 2018) stand out as one of the main protagonists. One interesting aspect of CAVs is that their computation requires sampling random examples from the train set. Therefore, the actual vectors obtained may vary depending on the randomness of this sampling. In this paper, we propose a fine-grained theoretical analysis of CAV construction in order to quantify their variability. Our results, confirmed by experiments on several real-life datasets of four different modalities, point to an universal result: the variance of CAVs declines roughly as 1/N1/N, where NN is the number of random examples. Based on this, we give practical recommendations for a resource-efficient application of the method.
Aug 8, 2025

Leveraging generative AI for human understanding: meta-requirements and design principles for Explanatory AI as an emerging paradigm

Artificial intelligence (AI) systems increasingly support decision-making across critical domains, yet explainable AI (XAI) approaches prioritise algorithmic transparency over human comprehension. While XAI reveals computational processes for model validation, end users require explanations integrating domain knowledge, contextual reasoning, and professional frameworks. This disconnect reveals a design challenge: existing approaches fail to address how practitioners need to understand and act upon AI recommendations. This paper introduces Explanatory AI as an emerging complementary paradigm where AI systems leverage generative and multimodal capabilities to serve as explanatory partners for human understanding. Unlike traditional XAI, which answers 'How did the algorithm decide?' for validation purposes, Explanatory AI addresses 'Why does this make sense?' for practitioners making informed decisions. Through theory-informed design, we synthesise multidisciplinary perspectives from cognitive science, communication research, and education with empirical evidence from healthcare and AI expert interviews. Our analysis identifies five dimensions distinguishing Explanatory AI from XAI: explanatory purpose, communication mode, epistemic stance, adaptivity, and cognitive design. We derive five meta-requirements and formulate ten design principles prescribing how to build such systems, illustrated through five UI mockups exemplifying implementation. Explanatory AI operates standalone or combined with XAI, serving distinct purposes in creating systems that genuinely support human reasoning and decision-making.
Jul 16, 2025

A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs

The success of recent Artificial Intelligence (AI) models has been accompanied by the opacity of their internal mechanisms, due notably to the use of deep neural networks. In order to understand these internal mechanisms and explain the output of these AI models, a set of methods have been proposed, grouped under the domain of eXplainable AI (XAI). This paper focuses on a sub-domain of XAI, called eXplainable Reinforcement Learning (XRL), which aims to explain the actions of an agent that has learned by reinforcement learning. We propose an intuitive taxonomy based on two questions "What" and "How". The first question focuses on the target that the method explains, while the second relates to the way the explanation is provided. We use this taxonomy to provide a state-of-the-art review of over 250 papers. In addition, we present a set of domains close to XRL, which we believe should get attention from the community. Finally, we identify some needs for the field of XRL.
Jun 30, 2025

Position: Use Sparse Autoencoders to Discover Unknowns

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives surrounding SAEs. We argue that even if SAEs may be less effective for acting on known concepts, SAEs are especially powerful tools for discovering unknown concepts. This distinction separates existing negative results from positive results, and suggests several classes of SAE applications. Specifically, we outline use cases for SAEs in (i) ML interpretability, explainability, fairness, auditing, and safety, and (ii) social and health sciences.
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.
Feb 6, 2025

Explanation Design in Strategic Learning: Sufficient Explanations That Induce Non-harmful Responses

We study the design of explanations in algorithmic decision-making with strategic agents, individuals who may modify their inputs in response to explanations of a decision maker's (DM's) predictive model. While the demand for algorithmic transparency has led much prior work to assume full model disclosure, in practice DMs typically provide only partial information via explanations, which can cause agents to misinterpret the model and take actions that unintentionally reduce their own utility. A central open question is therefore how DMs should communicate explanations that avoid harming strategic agents while still supporting their own goals, e.g., minimising predictive error. In this work, we analyse widely used explanation methods and establish a necessary condition to prevent explanations from inducing self-harming responses. Furthermore, we show that action recommendation-based explanations (ARexes), which encompass counterfactual explanations, are sufficient to induce all non-harmful responses. Under a conditional homogeneity assumption, this sufficiency extends to ARex-generating methods, echoing the revelation principle in information design. To demonstrate their practical utility, we introduce a simple learning procedure that jointly optimises the predictive model and the explanation-generating policy. Experiments on both synthetic and real-world tasks show that ARexes enable DMs to achieve high predictive performance while preserving agents' utility, offering a principled strategy for safe and effective partial model disclosure.
Oct 7, 2024

When Explanations Compete: Policy-Aware Selection Under Uncertainty

Uncertainty-aware explanation methods often produce several alternatives for the same prediction. Selecting among them requires a policy for balancing prediction confidence, uncertainty, and application constraints. This paper presents a framework for applying such policies to a fixed set of generated explanations. Candidates are characterised by uncertainty change, prediction direction, and, when available, interval position relative to a decision boundary. The framework combines these properties with eligibility rules, optional bidirectional Pareto screening, and policy-aware ranking. A fictitious prostate-cancer example illustrates how different explanatory purposes lead to different selections from the same candidate set. We instantiate the framework with Calibrated Explanations for classification, thresholded regression, and plain regression. Across 41 benchmark datasets, mean candidate counts range from 11.57 to 21.75 for single-feature explanations and from 29.4829.48 to 69.5369.53 when conjunctions are included. Equal-weight and confidence-only policies yield an average selection-disagreement rate of 28.7%28.7\% while favouring the same confidence direction. A supporting δδ-CLUE experiment demonstrates use with a second generator. By making the selection policy explicit, the framework allows applications to compare and prioritise explanations according to their intended use.
Jul 22, 2024

The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine learning models limits the use of conventional avenues of approach towards certifying complex technical systems. As a potential solution, methods to give insights into this black-box - devised in the field of eXplainable AI (XAI) - could be used. In this study, the potential and shortcomings of such methods for the purpose of safe AI development and certification are discussed in 15 qualitative interviews with experts out of the areas of (X)AI and certification. We find that XAI methods can be a helpful asset for safe AI development, as they can show biases and failures of ML-models, but since certification relies on comprehensive and correct information about technical systems, their impact is expected to be limited.
Jul 12, 2024

Unexplainability of Artificial Intelligence Judgments and Functional Implementation in Kant's Perspective

Kant's Critique of Pure Reason, a major contribution to the history of epistemology, proposes a table of categories to elucidate the structure of the a priori principles underlying human judgment. Artificial intelligence (AI) technology claims to simulate or replicate human judgment. To evaluate this claim, it is necessary to examine whether AI judgments exhibit the essential characteristics of human judgment. This paper investigates the unexplainability of AI judgments through the lens of Kant's theory of judgment. Drawing on Kant's four logical forms - quantity, quality, relation, and modality - this study identifies what may be called AI's uncertainty, a condition in which different forms of judgment become entangled. In particular, with regard to modality, this study argues that the Softmax function forcibly reframes AI judgments as possibility judgments. Furthermore, drawing on Kant's account of definition, this paper argues that no definitive criterion exists for verifying functional implementation. Moreover, fluent linguistic behavior may create the appearance of functional implementation even when important functions remain absent.