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

• URL: http://arxiv.org/abs/2510.14538v1
• Date: Thu, 16 Oct 2025 10:28:34 GMT
• Title: Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
• Authors: Emanuele Marconato, Samuele Bortolotti, Emile van Krieken, Paolo Morettin, Elena Umili, Antonio Vergari, Efthymia Tsamoura, Andrea Passerini, Stefano Teso,
• Abstract summary: Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding.<n>NeSy models can be affected by Reasoning Shortcuts (RSs)<n>RSs can compromise the interpretability of the model's explanations, performance in out-of-distribution scenarios, and therefore reliability.<n>This overview addresses this issue by providing a gentle introduction to RSs, discussing their causes and consequences in intuitive terms.
• Score: 30.036038864025457
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI [6.518655316889539]
  Neurosymbolic AI is growing in popularity thanks to its ability to combine neural perception and symbolic reasoning.<n>In this paper, we address reasoning shortcuts at their root cause and we introduce prototypical neurosymbolic architectures.<n>Our findings pave the way to prototype grounding as an effective, annotation-efficient strategy for safe and reliable neurosymbolic learning.
  arXiv  Detail & Related papers  (2025-10-29T13:21:28Z)
• Formal Explanations for Neuro-Symbolic AI [28.358183683756028]
  This paper proposes a formal approach to explaining the decisions of neuro-symbolic systems. It first computes a formal explanation for the symbolic component of the system, which serves to identify a subset of the individual parts of neural information that needs to be explained. This is followed by explaining only those individual neural inputs, independently of each other, which facilitates succinctness of hierarchical formal explanations.
  arXiv  Detail & Related papers  (2024-10-18T07:08:31Z)
• A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts [20.860617965394848]
  We introduce rsbench, a benchmark suite designed to systematically evaluate the impact of reasoning shortcuts on models. Using rsbench, we highlight that obtaining high quality concepts in both purely neural and neuro-symbolic models is a far-from-solved problem.
  arXiv  Detail & Related papers  (2024-06-14T18:52:34Z)
• Simple and Effective Transfer Learning for Neuro-Symbolic Integration [50.592338727912946]
  A potential solution to this issue is Neuro-Symbolic Integration (NeSy), where neural approaches are combined with symbolic reasoning. Most of these methods exploit a neural network to map perceptions to symbols and a logical reasoner to predict the output of the downstream task. They suffer from several issues, including slow convergence, learning difficulties with complex perception tasks, and convergence to local minima. This paper proposes a simple yet effective method to ameliorate these problems.
  arXiv  Detail & Related papers  (2024-02-21T15:51:01Z)
• BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts [21.743306538494043]
  Reasoning Shortcuts can affect Neuro-Symbolic (NeSy) predictors. They learn concepts consistent with symbolic knowledge by exploiting unintended semantics. We propose to ensure NeSy models are aware of the semantic ambiguity of the concepts they learn.
  arXiv  Detail & Related papers  (2024-02-19T15:54:36Z)
• The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning [54.56905063752427]
  Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems. Existing pipelines that train the neural and symbolic components sequentially require extensive labelling. New architecture, NeSyGPT, fine-tunes a vision-language foundation model to extract symbolic features from raw data.
  arXiv  Detail & Related papers  (2024-02-02T20:33:14Z)
• Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts [24.390922632057627]
  Neuro-Symbolic (NeSy) predictive models hold the promise of improved compliance with given constraints. They allow to infer labels that are consistent with some prior knowledge by reasoning over high-level concepts extracted from sub-symbolic inputs. It was recently shown that NeSy predictors are affected by reasoning shortcuts: they can attain high accuracy but by leveraging concepts with unintended semantics, thus coming short of their promised advantages.
  arXiv  Detail & Related papers  (2023-05-31T15:35:48Z)
• NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants [73.85768093666582]
  We propose an explainable geometric deep network dubbed NeuroExplainer. NeuroExplainer is used to uncover altered infant cortical development patterns associated with preterm birth.
  arXiv  Detail & Related papers  (2023-01-01T12:48:12Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting [135.0863818867184]
  artificial neural variability (ANV) helps artificial neural networks learn some advantages from natural'' neural networks. ANV plays as an implicit regularizer of the mutual information between the training data and the learned model. It can effectively relieve overfitting, label noise memorization, and catastrophic forgetting at negligible costs.
  arXiv  Detail & Related papers  (2020-11-12T06:06:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.