Cover Image

Neurosymbolic Reasoning Shortcuts under the Independence Assumption

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	van Krieken, Emile, Minervini, Pasquale, Ponti, Edoardo, Vergari, Antonio
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Independence Assumption in Neurosymbolic Learning
by: van Krieken, Emile, et al.
Published: (2024)

Neurosymbolic Diffusion Models
by: van Krieken, Emile, et al.
Published: (2025)

Mixtures of In-Context Learners
by: Hong, Giwon, et al.
Published: (2024)

Optimisation in Neurosymbolic Learning Systems
by: van Krieken, Emile
Published: (2024)

Fast and Expressive Multi-Token Prediction with Probabilistic Circuits
by: Grivas, Andreas, et al.
Published: (2025)

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
by: Marconato, Emanuele, et al.
Published: (2024)

A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
by: Bortolotti, Samuele, et al.
Published: (2024)

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
by: Marconato, Emanuele, et al.
Published: (2025)

Probing the Emergence of Cross-lingual Alignment during LLM Training
by: Wang, Hetong, et al.
Published: (2024)

Gradient-Based Optimization on Gödel Logic as Discrete Local Search
by: Daniele, Alessandro, et al.
Published: (2025)

ULLER: A Unified Language for Learning and Reasoning
by: van Krieken, Emile, et al.
Published: (2024)

Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
by: Andolfi, Luca, et al.
Published: (2025)

On the Theoretical Limitations of Embedding-based Link Prediction
by: Badreddine, Samy, et al.
Published: (2025)

Is Complex Query Answering Really Complex?
by: Gregucci, Cosimo, et al.
Published: (2024)

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
by: Younesian, Taraneh, et al.
Published: (2023)

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages
by: Ghazaryan, Gayane, et al.
Published: (2024)

Towards Logically Consistent Language Models via Probabilistic Reasoning
by: Calanzone, Diego, et al.
Published: (2024)

Low-Rank Compression of Language Models via Differentiable Rank Selection
by: Sundrani, Sidhant, et al.
Published: (2025)

Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $τ$-Mixing
by: Halgryn, Leon, et al.
Published: (2026)

Temporal Smoothness Regularisers for Neural Link Predictors
by: Dileo, Manuel, et al.
Published: (2023)

Even More Guarantees for Variational Inference in the Presence of Symmetries
by: Zellinger, Lena, et al.
Published: (2026)

FLARE: Faithful Logic-Aided Reasoning and Exploration
by: Arakelyan, Erik, et al.
Published: (2024)

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation
by: Chen, Weixin, et al.
Published: (2026)

Graphical Modelling without Independence Assumptions for Uncentered Data
by: Andrew, Bailey, et al.
Published: (2024)

On Faster Marginalization with Squared Circuits via Orthonormalization
by: Loconte, Lorenzo, et al.
Published: (2024)

An Auditing Test To Detect Behavioral Shift in Language Models
by: Richter, Leo, et al.
Published: (2024)

Adapting Time Series Foundation Models through Data Mixtures
by: Lee, Thomas L., et al.
Published: (2026)

Self-Training Large Language Models for Tool-Use Without Demonstrations
by: Luo, Ne, et al.
Published: (2025)

Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
by: Wójcik, Bartosz, et al.
Published: (2023)

Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification
by: Grivas, Andreas, et al.
Published: (2023)

Reasoning in Transformers -- Mitigating Spurious Correlations and Reasoning Shortcuts
by: Enström, Daniel, et al.
Published: (2024)

An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
by: Javaloy, Adrián, et al.
Published: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
by: Tyukin, Georgy, et al.
Published: (2024)

Modular Deep Learning
by: Pfeiffer, Jonas, et al.
Published: (2023)

Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning
by: Redman, William T., et al.
Published: (2026)

Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
by: Dhanraj, Varun, et al.
Published: (2025)

How to Square Tensor Networks and Circuits Without Squaring Them
by: Loconte, Lorenzo, et al.
Published: (2025)

COPA: Comparing the incomparable in multi-objective model evaluation
by: Javaloy, Adrián, et al.
Published: (2025)

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
by: Li, Jiayi, et al.
Published: (2026)

On the Hardness of Probabilistic Neurosymbolic Learning
by: Maene, Jaron, et al.
Published: (2024)