Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems

• URL: http://arxiv.org/abs/2607.21185v1
• Date: Thu, 23 Jul 2026 11:15:19 GMT
• Title: Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems
• Abstract summary: We propose a novel method using matrix-based differentiable logic programming to mitigate reasoning shortcuts.<n>We introduce design elements to mitigate shortcuts, including a unified encoding of rules and constraints in a single matrix.<n>We show that one-to-one grounding of neural outputs to logical atoms significantly reduces both shortcut types.
• Score: 4.79123314326423
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has shown they are susceptible to shortcut reasoning behaviors. We propose a novel method using matrix-based differentiable logic programming to mitigate reasoning shortcuts in two phenomena: constraint satisfaction shortcuts, where constraints are satisfied without achieving the intended task, and cognition shortcuts, where biased data leads to semantically incorrect concept mappings despite logically sound inference. Building on recent matrix-based logic programming semantics, we introduce design elements to mitigate shortcuts, including a unified encoding of rules and constraints in a single matrix. We also identify connections to fuzzy logic t-norms and empirically compare their gradient flow properties. Through carefully designed experiments on MNIST variants, we show that one-to-one grounding of neural outputs to logical atoms significantly reduces both shortcut types compared to previous methods that rely on soft probability distributions. We then confirm that architectural choices in coupling symbolic knowledge with neural learning play a critical role in shortcut mitigation.

Related papers

• Quantitative Linear Logic for Neuro-Symbolic Learning and Verification [0.6299766708197881]
  Differentiable Logics are deployed in neuro-symbolic learning tasks as a way of embedding logical constraints in the training objective of neural networks.<n>A defining trade-off of the field is that between logical properties of the connectives, and analytic concerns for the semantics.<n>We propose a resolution to this long-standing tension via a novel logic, Quantitative Linear Logic.
  arXiv  Detail & Related papers  (2026-05-13T17:59:40Z)
• 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)
• Learning with Logical Constraints but without Shortcut Satisfaction [23.219364371311084]
  We present a new framework for learning with logical constraints. Specifically, we address the shortcut satisfaction issue by introducing dual variables for logical connectives. We propose a variational framework where the encoded logical constraint is expressed as a distributional loss.
  arXiv  Detail & Related papers  (2024-03-01T07:17:20Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation [85.12429517510311]
  LogicDiag is a neural-logic semi-supervised learning framework for semantic segmentation. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules.
  arXiv  Detail & Related papers  (2023-08-24T06:50:07Z)
• Injecting Logical Constraints into Neural Networks via Straight-Through Estimators [5.6613898352023515]
  Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, could effectively be applied to incorporate logical constraints into neural network learning.
  arXiv  Detail & Related papers  (2023-07-10T05:12:05Z)
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks [65.23508422635862]
  We propose learning rules with the recently proposed logical neural networks (LNN) Compared to others, LNNs offer strong connection to classical Boolean logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable.
  arXiv  Detail & Related papers  (2021-12-06T19:38:30Z)
• Reinforcement Learning with External Knowledge by using Logical Neural Networks [67.46162586940905]
  A recent neuro-symbolic framework called the Logical Neural Networks (LNNs) can simultaneously provide key-properties of both neural networks and symbolic logic. We propose an integrated method that enables model-free reinforcement learning from external knowledge sources.
  arXiv  Detail & Related papers  (2021-03-03T12:34:59Z)
• Relaxing the Constraints on Predictive Coding Models [62.997667081978825]
  Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs is the minimization of prediction errors. Standard implementations of the algorithm still involve potentially neurally implausible features such as identical forward and backward weights, backward nonlinear derivatives, and 1-1 error unit connectivity. In this paper, we show that these features are not integral to the algorithm and can be removed either directly or through learning additional sets of parameters with Hebbian update rules without noticeable harm to learning performance.
  arXiv  Detail & Related papers  (2020-10-02T15:21:37Z)
• Logical Neural Networks [51.46602187496816]
  We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning) Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omni rather than focused on predefined target variables, and corresponds to logical reasoning.
  arXiv  Detail & Related papers  (2020-06-23T16:55:45Z)

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.