# A Symbolic Approach for Counterfactual Explanations

arXiv: https://arxiv.org/abs/2206.09638 · HTML: https://mlsanity.com/paper/2206.09638/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 20 Jun 2022.

## Builds on (most cited first, 2 of 2)

- [A Symbolic Approach to Explaining Bayesian Network Classifiers](https://mlsanity.com/paper/1805.03364/) (2018)
- [On Tractable Representations of Binary Neural Networks](https://mlsanity.com/paper/2004.02082/) (2020)

## Built on by (most cited first, 5 of 5)

- [Logic-Based Explainability in Machine Learning](https://mlsanity.com/paper/2211.00541/) (2022)
- [ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanations](https://mlsanity.com/paper/2206.11900/) (2022)
- [Delivering Inflated Explanations](https://mlsanity.com/paper/2306.15272/) (2023)
- [A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration](https://mlsanity.com/paper/2206.11539/) (2022)
- [Ranking Counterfactual Explanations](https://mlsanity.com/paper/2503.15817/) (2025)

## Abstract (arXiv)

In this paper titled A Symbolic Approach for Counterfactual Explanations we propose a novel symbolic approach to provide counterfactual explanations for a classifier predictions. Contrary to most explanation approaches where the goal is to understand which and to what extent parts of the data helped to give a prediction, counterfactual explanations indicate which features must be changed in the data in order to change this classifier prediction. Our approach is symbolic in the sense that it is based on encoding the decision function of a classifier in an equivalent CNF formula. In this approach, counterfactual explanations are seen as the Minimal Correction Subsets (MCS), a well-known concept in knowledge base reparation. Hence, this approach takes advantage of the strengths of already existing and proven solutions for the generation of MCS. Our preliminary experimental studies on Bayesian classifiers show the potential of this approach on several datasets.