From Perception to Reasoning: Knowledge Graphs, Neuro-Symbolic AI, and Explainable Artificial Intelligence in Autonomous Vehicles

Hybrid Knowledge Graph and Large Language Model Architectures for Predictive Analytics

This paper presents a comprehensive framework integrating graph embeddings, retrieval-augmented generation (RAG), transformer-based reasoning, attention mechanisms, and contextual embedding fusion to improve prediction accuracy, explainability, and robustness.

Hybrid Knowledge Graph and Large Language Model Architectures for Predictive Analytics

This paper reviews hybrid KG–LLM frameworks for predictive analytics, highlighting graph embeddings, Retrieval-Augmented Generation (RAG), transformer-based reasoning, and contextual embedding fusion to improve prediction accuracy, interpretability, and robustness.

Integrating and Reasoning with Data-Induced Information: Knowledge Bases of Axioms and Learned Models

Mitigating Neuro-Symbolic Reasoning Shortcuts with Data-Driven Knowledge Augmentation

Recent advancements in neuro-symbolic learning (NeSy) have shown significant promise in integrating deep learning with symbolic reasoning, offering both interpretability and generalization. However, the prevalence of reasoning shortcuts, where the NeSy system predicts incorrect intermediate concepts while maintaining high final accuracy, poses a substantial challenge. This is especially problematic in domains requiring reliable and transparent decision-making. Inspired by recent theories, we find that existing methods fail to address the reasoning shortcut issue when the knowledge base lacks sufficient complexity, highlighting their vulnerability in real-world applications. In this work, we present a novel method called DKA to address this issue. It introduces a limited set of concept-supervised data to enhance the knowledge base, effectively solving the reasoning shortcut problem and improving the applicability of the NeSy system. Theoretical analysis reveals that DKA can reduce shortcut risks with improved data efficiency. Empirical studies across multiple tasks within various neuro-symbolic frameworks also verify the effectiveness of the DKA method.

Generative AI in Transportation Analytics: Foundations, Deep Generative Models, and Practical Use Cases

Generative artificial intelligence (Gen-AI) is rapidly reshaping transportation analytics by enabling data synthesis, uncertainty modeling, and decision-oriented reasoning under sparse and complex conditions. This study presents a systematic, use-case-driven review of 142 empirical transportation studies published between 2018 and August 2025, synthesizing how Gen-AI has been adapted, evaluated, and integrated into real transportation workflows. This study distinguishes two dominant model families, deep generative models and foundation models, and show that they serve fundamentally different yet increasingly complementary roles: the former addressing data scarcity and distributional learning, and the latter enabling reasoning, coordination, and decision support. Through bibliometric analysis, topic modeling, and application mapping, this study identifies major adoption trends, persistent limitations, and research gaps related to generalization, validation, scalability, and trust. The findings reveal a field-level shift from prediction-centric modeling toward generative, decision-aware transportation intelligence and outline a roadmap for responsible, domain-grounded deployment of Gen-AI in safety-critical transportation systems.

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g., safety or structural constraints. As such, it represents one of the most promising avenues for reliable and trustworthy AI. The core idea behind NeSy AI is to combine neural and symbolic steps: neural networks are typically responsible for mapping low-level inputs into high-level symbolic concepts, while symbolic reasoning infers predictions compatible with the extracted concepts and the prior knowledge. Despite their promise, it was recently shown that – whenever the concepts are not supervised directly – NeSy models can be affected by Reasoning Shortcuts (RSs). That is, they can achieve high label accuracy by grounding the concepts incorrectly. RSs can compromise the interpretability of the model’s explanations, performance in out-of-distribution scenarios, and therefore reliability. At the same time, RSs are difficult to detect and prevent unless concept supervision is available, which is typically not the case. However, the literature on RSs is scattered, making it difficult for researchers and practitioners to understand and tackle this challenging problem. This overview addresses this issue by providing a gentle introduction to RSs, discussing their causes and consequences in intuitive terms. It also reviews and elucidates existing theoretical characterizations of this phenomenon. Finally, it details methods for dealing with RSs, including mitigation and awareness strategies, and maps their benefits and limitations. By reformulating advanced material in a digestible form, this overview aims to provide a unifying perspective on RSs to lower the bar to entry for tackling them. Ultimately, we hope this overview contributes to the development of reliable NeSy and trustworthy AI models.