Right for the right reasons: avoiding reasoning shortcuts via prototypical neurosymbolic AI
Author(s)
Andolfi, Luca
Giunchiglia, Eleonora
Type
Conference Paper
Abstract
Neurosymbolic AI is growing in popularity thanks to its ability to combine neural perception and symbolic reasoning in end-to-end trainable models. However, recent findings reveal these are prone to shortcut reasoning, i.e., to learning unindented concepts--or neural predicates--which exploit spurious correlations to satisfy the symbolic constraints. In this paper, we address reasoning shortcuts at their root cause and we introduce Prototypical Neurosymbolic architectures. These models are able to satisfy the symbolic constraints (be right) because they have learnt the correct basic concepts (for the right reasons) and not because of spurious correlations, even in extremely low data regimes. Leveraging the theory of prototypical learning, we demonstrate that we can effectively avoid reasoning shortcuts by training the models to satisfy the background knowledge while taking into account the similarity of the input with respect to the handful of labelled datapoints. We extensively validate our approach on the recently proposed rsbench benchmark suite in a variety of settings and tasks with very scarce supervision: we show significant improvements in learning the right concepts both in synthetic tasks (MNIST-EvenOdd and Kand-Logic) and real-world, high-stake ones (BDD-OIA). Our findings pave the way to prototype grounding as an effective, annotation-efficient strategy for safe and reliable neurosymbolic learning.
Date Issued
2025-12-02
Date Acceptance
2025-09-18
Citation
Advances in Neural Information Processing Systems 38, 2025, 38, pp.157309-157343
Publisher
Curran Associates, Inc.
Start Page
157309
End Page
157343
Journal / Book Title
Advances in Neural Information Processing Systems 38
Volume
38
Copyright Statement
© 2025 NeurIPS.
Source
39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Publication Status
Published
Start Date
2025-12-02
Finish Date
2025-12-07
Coverage Spatial
San Diego, CA, USA