Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation
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_ | 1866917659451326464 |
|---|---|
| author | Alfano, Gianvincenzo Greco, Sergio Parisi, Francesco Trubitsyna, Irina |
| author_facet | Alfano, Gianvincenzo Greco, Sergio Parisi, Francesco Trubitsyna, Irina |
| contents | Explainable Artificial Intelligence and Formal Argumentation have received significant attention in recent years. Argumentation-based systems often lack explainability while supporting decision-making processes. Counterfactual and semifactual explanations are interpretability techniques that provide insights into the outcome of a model by generating alternative hypothetical instances. While there has been important work on counterfactual and semifactual explanations for Machine Learning models, less attention has been devoted to these kinds of problems in argumentation. In this paper, we explore counterfactual and semifactual reasoning in abstract Argumentation Framework. We investigate the computational complexity of counterfactual- and semifactual-based reasoning problems, showing that they are generally harder than classical argumentation problems such as credulous and skeptical acceptance. Finally, we show that counterfactual and semifactual queries can be encoded in weak-constrained Argumentation Framework, and provide a computational strategy through ASP solvers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04081 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation Alfano, Gianvincenzo Greco, Sergio Parisi, Francesco Trubitsyna, Irina Artificial Intelligence Explainable Artificial Intelligence and Formal Argumentation have received significant attention in recent years. Argumentation-based systems often lack explainability while supporting decision-making processes. Counterfactual and semifactual explanations are interpretability techniques that provide insights into the outcome of a model by generating alternative hypothetical instances. While there has been important work on counterfactual and semifactual explanations for Machine Learning models, less attention has been devoted to these kinds of problems in argumentation. In this paper, we explore counterfactual and semifactual reasoning in abstract Argumentation Framework. We investigate the computational complexity of counterfactual- and semifactual-based reasoning problems, showing that they are generally harder than classical argumentation problems such as credulous and skeptical acceptance. Finally, we show that counterfactual and semifactual queries can be encoded in weak-constrained Argumentation Framework, and provide a computational strategy through ASP solvers. |
| title | Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.04081 |