# Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

arXiv: https://arxiv.org/abs/1802.07384 · HTML: https://mlsanity.com/paper/1802.07384/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2018.

## Built on by (most cited first, 19 of 19)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice](https://mlsanity.com/paper/2103.14651/) (2021)
- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [VeriX: Towards Verified Explainability of Deep Neural Networks](https://mlsanity.com/paper/2212.01051/) (2022)
- [Provably Bounding Neural Network Preimages](https://mlsanity.com/paper/2302.01404/) (2023)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)
- [XAIR: A Framework of Explainable AI in Augmented Reality](https://mlsanity.com/paper/2303.16292/) (2023)
- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [Interpretable Machine Learning: Moving From Mythos to Diagnostics](https://mlsanity.com/paper/2103.06254/) (2021)
- [Cardinality-Minimal Explanations for Monotonic Neural Networks](https://mlsanity.com/paper/2205.09901/) (2022)
- [Provably Safe Neural Network Controllers via Differential Dynamic Logic](https://mlsanity.com/paper/2402.10998/) (2024)
- [ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques](https://mlsanity.com/paper/2209.03798/) (2022)
- [Sparse and Faithful Explanations Without Sparse Models](https://mlsanity.com/paper/2402.09702/) (2024)
- [Synthesizing Pareto-Optimal Interpretations for Black-Box Models](https://mlsanity.com/paper/2108.07307/) (2021)
- [Instructive artificial intelligence (AI) for human training, assistance, and explainability](https://mlsanity.com/paper/2111.01726/) (2021)
- [Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions](https://mlsanity.com/paper/2302.04791/) (2023)

## Abstract (arXiv)

We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue that such a correction is a useful way to provide feedback to a user when the network's output is different from a desired output. Our algorithm generates such a correction by solving a series of linear constraint satisfaction problems. The technique is evaluated on three neural network models: one predicting whether an applicant will pay a mortgage, one predicting whether a first-order theorem can be proved efficiently by a solver using certain heuristics, and the final one judging whether a drawing is an accurate rendition of a canonical drawing of a cat.