Explainable AI the Latest Advancements and New Trends
Not on the map. Why?
Abstract (arXiv)
In recent years, Artificial Intelligence technology has excelled in various applications across all domains and fields. However, the various algorithms in neural networks make it difficult to understand the reasons behind decisions. For this reason, trustworthy AI techniques have started gaining popularity. The concept of trustworthiness is cross-disciplinary; it must meet societal standards and principles, and technology is used to fulfill these requirements. In this paper, we first surveyed developments from various countries and regions on the ethical elements that make AI algorithms trustworthy; and then focused our survey on the state of the art research into the interpretability of AI. We have conducted an intensive survey on technologies and techniques used in making AI explainable. Finally, we identified new trends in achieving explainable AI. In particular, we elaborate on the strong link between the explainability of AI and the meta-reasoning of autonomous systems. The concept of meta-reasoning is 'reason the reasoning', which coincides with the intention and goal of explainable Al. The integration of the approaches could pave the way for future interpretable AI systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 57 of its 133 references that are in the map. First posted on arXiv 11 May 2025.
Builds on
57 of 133 references.
References · 57
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2015VQA: Visual Question Answeringcited by 2,506
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
38 more
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
- 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
- 2018Efficient Low-rank Multimodal Fusion with Modality-Specific Factorscited by 270
- 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
- 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
- 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
- 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 166
- 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
- 2015Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction modelcited by 140
- 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
- 2023Large Language Models as Analogical Reasonerscited by 107
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2021Trustworthy AI: A Computational Perspectivecited by 93
- 2015A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classificationcited by 92
- 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
- 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
- 2015Supersparse Linear Integer Models for Optimized Medical Scoring Systemscited by 76
- 2020One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparencycited by 64
- 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
- 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
- 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
- 2018Visualizing the Feature Importance for Black Box Modelscited by 55
- 2018Do Explanations make VQA Models more Predictable to a Human?cited by 52
- 2018Explanation Methods in Deep Learning: Users, Values, Concerns and Challengescited by 49
- 2020Multimodal Prototypical Networks for Few-shot Learningcited by 48
- 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 47
- 2017Interpretability via Model Extractioncited by 40
- 2021Feature-based Style Randomization for Domain Generalizationcited by 34
- 2018TED: Teaching AI to Explain its Decisionscited by 33
- 2019Do Human Rationales Improve Machine Explanations?cited by 33
- 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 32
- 2024Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendationscited by 31
- 2021On the Sensitivity and Stability of Model Interpretations in NLPcited by 30
- 2024Meta Reasoning for Large Language Modelscited by 29
- 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 27
- 2016Rule Extraction Algorithm for Deep Neural Networks: A Reviewcited by 22
- 2018Global Model Interpretation via Recursive Partitioningcited by 17
- 2015Distilling Knowledge from Deep Networks with Applications to Healthcare Domaincited by 16
50 most cited of 57 All 57 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026An Agentic Approach to Generating XAI-Narrativescited by 4
- 2026An Agentic Approach to Generating XAI-Narratives20 Mar 2026