# "Why did you do that?": Explaining black box models with Inductive Synthesis

## TL;DR

This paper introduces RICE, a novel method that generates human-readable explanations for black box models by combining sensitivity analysis, inductive logic programming, and interpretation, demonstrated on a neural network in a traffic simulation.

## Contribution

The paper presents RICE, a new approach that synthesizes logic-based explanations for black box models using critical input-output pairs and inductive logic programming.

## Key findings

- Successfully generated explanations for neural network behavior in traffic rules
- Demonstrated scalability and usability of RICE in explanation-critical scenarios
- Enhanced interpretability of black box models through logic program synthesis

## Abstract

By their nature, the composition of black box models is opaque. This makes the ability to generate explanations for the response to stimuli challenging. The importance of explaining black box models has become increasingly important given the prevalence of AI and ML systems and the need to build legal and regulatory frameworks around them. Such explanations can also increase trust in these uncertain systems. In our paper we present RICE, a method for generating explanations of the behaviour of black box models by (1) probing a model to extract model output examples using sensitivity analysis; (2) applying CNPInduce, a method for inductive logic program synthesis, to generate logic programs based on critical input-output pairs; and (3) interpreting the target program as a human-readable explanation. We demonstrate the application of our method by generating explanations of an artificial neural network trained to follow simple traffic rules in a hypothetical self-driving car simulation. We conclude with a discussion on the scalability and usability of our approach and its potential applications to explanation-critical scenarios.