181 articles tagged with #explainable-ai. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
This arXiv survey examines explainable AI (XAI) methods applied to Answer Set Programming (ASP), a symbolic AI approach used for declarative reasoning. The paper catalogs existing explanation approaches and tools while identifying gaps in coverage across different user scenarios, establishing a foundation for future XAI research in logic-based systems.
Researchers present an LLM-augmented explainable AI framework that generates human-readable explanations for network operations by combining SHAP feature analysis with mutual feature interactions. The approach demonstrates 12.2% improvement in explanation usefulness over baseline methods while maintaining 97.5% correctness, addressing the critical gap between opaque AI/ML models and operator trust in network infrastructure.
Researchers have significantly improved NeurASP, a neurosymbolic AI framework that combines neural networks with symbolic reasoning, through vectorization, batch processing, and caching techniques. The enhancements achieve speedups of multiple orders of magnitude, addressing previous computational bottlenecks that limited scalability for complex tasks.
Researchers challenge the conventional wisdom that information leakage in concept-based neural networks is inherently harmful, arguing that some leakage is necessary for building accurate and practical AI systems. The paper proposes that 'benign leakage' can coexist with interpretability when concept descriptions are incomplete, reframing how these models should be optimized.
A systematic literature review examines Self-Explainability (SX) in self-adaptive and self-organizing systems, finding that most approaches remain theoretical with no standardized evaluation methods. The research establishes a taxonomy and framework for advancing SX, identifying a significant gap between conceptual work and practical implementation in increasingly complex AI-driven systems.
Researchers introduce XAInomaly, an explainable AI framework using a Semi-supervised Deep Contractive Autoencoder for detecting anomalies in Open RAN (O-RAN) networks. The system addresses the critical need for interpretable machine learning in complex wireless infrastructure by combining generative modeling with explainability techniques to identify network traffic deviations while maintaining transparency in decision-making.
Researchers propose Comp-MCTS, an AI framework that efficiently generates multiple counterfactual explanations under limited LLM budget constraints by using tree-search algorithms to allocate queries toward novel intervention directions. The approach demonstrates superior performance in producing diverse, validated counterfactuals compared to existing single-candidate and multi-candidate baselines on real-world datasets.
Researchers introduce SAILS, a model-agnostic framework that goes beyond detecting feature interactions in machine learning models to reveal their functional forms and characteristics. Using surrogate generalized additive models, SAILS categorizes interactions as linear, product-separable, or non-product-separable and provides tailored visualizations, advancing the field of explainable AI.
Researchers have developed SleepExplain, a machine learning model that classifies sleep stages (NREM and REM) from EEG signals with 94.30% accuracy using XGBoost, while employing SHAP explainability techniques to make predictions interpretable. This advancement bridges clinical diagnostics and AI transparency, addressing a critical need in sleep disorder diagnosis where understanding model reasoning is as important as accuracy.
Researchers present a method to extract interpretable programs from trained Transformers by converting them to RASP (a simple programming language) and using causal interventions to identify minimal sub-programs. Experiments on algorithmic tasks demonstrate that length-generalizing Transformers often implement simple, understandable algorithms internally, providing direct evidence that neural networks discover human-readable solutions.
Researchers propose a Cognitive Threat Intelligence framework combining Federated Learning and Explainable AI to detect cyber threats across distributed infrastructure systems while preserving data privacy. The approach eliminates the need to transmit sensitive network traffic to centralized servers, instead training models locally and sharing only encrypted parameters.
Researchers present an XGBoost and SHAP-based intrusion detection framework for protecting U.S. critical infrastructure using explainable AI techniques. The study demonstrates how machine learning models combined with transparency mechanisms can enhance cybersecurity decision-making across energy, healthcare, transportation, and financial sectors.
Researchers introduce MechSim, a neuro-symbolic framework that enables large language models to reason transparently about the assumptions and mechanisms underlying scientific simulators. The approach improves explainability and decision-making reliability in high-stakes simulation-driven applications by treating simulators as structured systems rather than black boxes.
Researchers have developed synthetic benchmarks for concept bottleneck models—AI systems that make predictions based on high-level concepts rather than raw data. The benchmarks address a critical gap in the field by enabling controlled evaluation of these interpretable AI models across different use cases, from decision support to automation, while managing variables like data type and annotation quality.
Researchers introduce TBS (Think-Before-Speak), a multi-agent simulation framework that separates LLM agents' internal reasoning from public dialogue in social interactions. The framework tracks internal states like cognitive dissonance and speaking willingness, then orchestrates public utterances, enabling detailed analysis of how private evaluation drives public expression in collective deliberation scenarios.
A new academic framework proposes interaction as the primary unit of analysis for understanding intelligence in human-AI systems, shifting focus from isolated computation within individual models to the relational dynamics that emerge through collaborative engagement. The paper synthesizes decades of research across distributed cognition, embodied cognition, and computational creativity to argue that intelligence, creativity, and meaning arise from evolving interaction patterns rather than internal computation alone.
Researchers developed an explainable deep reinforcement learning framework for optimizing energy management in buildings with renewable sources, battery storage, and dynamic pricing. Testing on real-world data from KIT's Living Lab Energy Campus showed that on-policy algorithms (A2C, PPO) outperformed off-policy methods while providing transparent insights into decision-making processes.
Researchers introduce Hoeffding Concept Bottleneck Models (HCBM), a novel approach to explainable AI that uses non-linear aggregation of concept scores instead of traditional linear methods. The technique demonstrates improved performance on classification and object detection tasks while maintaining robustness against information leakage between concepts.
Researchers propose XAI-SOH-FL, an enhanced federated learning framework for IoT intrusion detection that combines adaptive aggregation mechanisms with explainable AI to address data heterogeneity and model interpretability challenges. The system achieves 94.12% accuracy on benchmark datasets while eliminating manual parameter tuning and providing transparent feature-level insights into security decisions.
TabChange is a new machine learning approach for modifying individual attributes in tabular datasets while maintaining data naturalness and minimizing unintended changes. The method analyzes attribute relationships and uses adversarial techniques to remove latent information about target attributes, producing more valid counterfactuals than existing generative models.
Researchers developed a method combining multi-agent deep reinforcement learning with explainable AI techniques to optimize drag reduction in turbulent flows, achieving 34.44% drag reduction with only 0.43% energy input—significantly outperforming traditional opposition control methods.
Researchers introduce TN-SHAP-G, a machine learning framework that efficiently computes Shapley values—a key method for explaining AI model decisions—by leveraging graph structure in data. The approach uses tensor networks to create compact surrogates that scale to larger datasets where traditional methods become computationally infeasible.
Researchers introduce PatentXAI, a framework using Shapley values and graph-conditioned Markov Blankets to fairly allocate patent valuations within complex products containing thousands of patents. The method scales computationally by restricting coalition analysis to relevant patent subsets, achieving sub-100 millisecond processing times while maintaining accuracy within 6.2% of Monte Carlo benchmarks.
Researchers introduce DhondtXAI, a novel explainable AI framework for tabular data that uses proportional representation principles (the D'Hondt rule) to attribute feature importance instead of relying on SHAP values. The method demonstrates high correlation with SHAP while offering complementary capabilities for handling feature interactions and alliances, validated across synthetic tests and healthcare datasets.
Researchers introduce Mixture of Concept Bottleneck Experts (M-CBE), a framework that enhances interpretable AI by allowing multiple expert expressions to map concepts to predictions rather than a single predetermined function. The approach combines Linear M-CBE and Symbolic M-CBE variants to improve both accuracy and adaptability while maintaining human-understandable decision-making processes.
