Natural Language Counterfactual Explanations for Graphs Using Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916583442481152 |
|---|---|
| author | Giorgi, Flavio Campagnano, Cesare Silvestri, Fabrizio Tolomei, Gabriele |
| author_facet | Giorgi, Flavio Campagnano, Cesare Silvestri, Fabrizio Tolomei, Gabriele |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_09295 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Natural Language Counterfactual Explanations for Graphs Using Large Language Models Giorgi, Flavio Campagnano, Cesare Silvestri, Fabrizio Tolomei, Gabriele Artificial Intelligence Computation and Language 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. |
| title | Natural Language Counterfactual Explanations for Graphs Using Large Language Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2410.09295 |