Natural Language Counterfactual Explanations for Graphs Using Large Language Models

Flavio Giorgi, Cesare Campagnano, Fabrizio Silvestri, Gabriele Tolomei
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:3565-3573, 2025.

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

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-giorgi25a, title = {Natural Language Counterfactual Explanations for Graphs Using Large Language Models}, author = {Giorgi, Flavio and Campagnano, Cesare and Silvestri, Fabrizio and Tolomei, Gabriele}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {3565--3573}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/giorgi25a/giorgi25a.pdf}, url = {https://proceedings.mlr.press/v258/giorgi25a.html}, 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} }
Endnote
%0 Conference Paper %T Natural Language Counterfactual Explanations for Graphs Using Large Language Models %A Flavio Giorgi %A Cesare Campagnano %A Fabrizio Silvestri %A Gabriele Tolomei %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-giorgi25a %I PMLR %P 3565--3573 %U https://proceedings.mlr.press/v258/giorgi25a.html %V 258 %X 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
APA
Giorgi, F., Campagnano, C., Silvestri, F. & Tolomei, G.. (2025). Natural Language Counterfactual Explanations for Graphs Using Large Language Models. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:3565-3573 Available from https://proceedings.mlr.press/v258/giorgi25a.html.

Related Material