Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction

Abstract

Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models.

References in corpus (52)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Towards A Rigorous Science of Interpretable Machine Learning
• Methods for Interpreting and Understanding Deep Neural Networks
• Striving for Simplicity: The All Convolutional Net
• A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
• Time Series Forecasting With Deep Learning: A Survey
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Explainable Machine Learning for Scientific Insights and Discoveries
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
• A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• Model-Agnostic Interpretability of Machine Learning
• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Attention is not Explanation
• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
• A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Natural Language Processing Advancements By Deep Learning: A Survey
• Modeling Missing Data in Clinical Time Series with RNNs
• Explainable Deep Reinforcement Learning: State of the Art and Challenges
• Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
• Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
• TSViz: Demystification of Deep Learning Models for Time-Series Analysis
• Larger language models do in-context learning differently
• Physically Explainable CNN for SAR Image Classification
• NExT-GPT: Any-to-Any Multimodal LLM
• Benchmarking Deep Learning Interpretability in Time Series Predictions
• Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies
• "Dave...I can assure you...that it's going to be all right..." -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships
• Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions
• Interpretability and Explainability: A Machine Learning Zoo Mini-tour
• Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
• A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learning
• A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
• Measuring Faithfulness in Chain-of-Thought Reasoning
• How Interpretable are Reasoning Explanations from Prompting Large Language Models?
• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango
• Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
• On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification
• Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
• Model Explainability in Deep Learning Based Natural Language Processing
• Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions
• Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
• Towards Safe, Explainable, and Regulated Autonomous Driving

Cited by in corpus (7)

• Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models
• Explainable AI: XAI-Guided Context-Aware Data Augmentation
• Enhancing Trust Through Standards: A Comparative Risk-Impact Framework for Aligning ISO AI Standards with Global Ethical and Regulatory Contexts
• Audio-visual cross-modality knowledge transfer for machine learning-based in-situ monitoring in laser additive manufacturing
• Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions
• Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
• Feature Attribution in 5G Intrusion Detection: A Statistical vs. Logic-Based Comparison