Neurosymbolic Reasoning Shortcuts under the Independence Assumption

Emile van Krieken, Pasquale Minervini, Edoardo Ponti, Antonio Vergari

Keywords: neurosymbolic predictors, reasoning shortcuts, independence assumption

TL;DR: We prove that neurosymbolic predictors with the independence assumption cannot be reasoning shortcut aware for the vast majority of problems

Abstract: The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic reasoning. Recent works like van Krieken et al. (2024) and Marconato et al. (2024) argued that the independence assumption can hinder learning of NeSy predictors and, more crucially, prevent them from correctly modelling uncertainty. There is, however, scepticism in the NeSy community around the scenarios in which the independence assumption actually limits NeSy systems (Faronius and Dos Martires, 2025). In this work, we settle this question by formally showing that assuming independence among symbolic concepts entails that a model can never represent uncertainty over certain concept combinations. Thus, the model fails to be aware of _reasoning shortcuts_, i.e., the pathological behaviour of NeSy predictors that predict correct downstream tasks but for the wrong reasons.

Track: Main Track

Paper Type: Long Paper

Resubmission: No

Software: https://github.com/HEmile/independence-vs-rs/tree/main

Submission Number: 34