Natural Language Counterfactual Explanations for Graphs Using Large Language Models
This work addresses the interpretability challenge for non-experts in Explainable AI by making counterfactual explanations more accessible, though it is incremental as it builds on existing explainers.
The paper tackled the problem of complex and technical counterfactual explanations for graph-based models by using open-source Large Language Models to generate natural language explanations, showing effective production of accurate representations across several datasets and explainers.
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.