Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era

2026-03-03

AI Summary

Neural-symbolic approaches face practical limitations due to weak semantic generalization, the difficulty of predefining complex rules, and growing skepticism about their competitiveness in the era of large language models. This work presents the first task-oriented systematic survey of neural-symbolic AI, focusing on integrating symbolic systems to enhance the interpretability and reasoning capabilities of black-box models. By analyzing task-specific hybrid architectures in domains such as natural language processing and computer vision, the study highlights the real-world utility of neural-symbolic methods. It further provides reproducible code and in-depth annotations, offering researchers a practical design guide for developing interpretable AI systems tailored to concrete tasks, thereby fostering the continued evolution of this paradigm amid the rise of large models.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to infer or exploit behavioral schema has been widely considered as one of the possible proxies for human-level intelligence. However, the limited semantic generalizability and the challenges in declining complex domains with pre-defined patterns and rules hinder their practical implementation in real-world scenarios. The unprecedented results achieved by connectionist systems since the last AI breakthrough in 2017 have raised questions about the competitiveness of NeSy solutions, with particular emphasis on the Natural Language Processing and Computer Vision fields. This survey examines task-specific advancements in the NeSy domain to explore how incorporating symbolic systems can enhance explainability and reasoning capabilities. Our findings are meant to serve as a resource for researchers exploring explainable NeSy methodologies for real-life tasks and applications. Reproducibility details and in-depth comments on each surveyed research work are made available at https://github.com/disi-unibo-nlp/task-oriented-neuro-symbolic.git.

Problem

• Neuro-Symbolic AI
• semantic generalizability
• pre-defined rules
• black-box models
• real-world applications

Innovation

• Neuro-Symbolic AI
• Explainability
• Task-Oriented Survey
• Symbolic Reasoning
• Black-Box Models