Natural Language Counterfactual Explanations for Graphs Using Large Language Models

TL;DR

This paper leverages large language models to generate natural language explanations for counterfactuals in graph-based models, enhancing interpretability for non-experts.

Contribution

It introduces a novel method using large language models to produce human-readable explanations of counterfactuals in graph models, bridging the interpretability gap.

Findings

Effective natural language representations of counterfactuals

High accuracy demonstrated across multiple datasets

Improved interpretability for non-expert users

Abstract

Explainable Artificial Intelligence (XAI) has emerged as a critical area of research to unravel the opaque inner logic of (deep) machine learning models. Among the various XAI techniques proposed in the literature, counterfactual explanations stand out as one of the most promising approaches. However, these "what-if" explanations are frequently complex and technical, making them difficult for non-experts to understand and, more broadly, challenging for humans to interpret. To bridge this gap, in this work, we exploit the power of open-source Large Language Models to generate natural language explanations when prompted with valid counterfactual instances produced by state-of-the-art explainers for graph-based models. Experiments across several graph datasets and counterfactual explainers show that our approach effectively produces accurate natural language representations of counterfactual instances, as demonstrated by key performance metrics.