Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916947337150464 |
|---|---|
| author | Armoni-Friedmann, Stav Chockler, Hana Kelly, David A. |
| author_facet | Armoni-Friedmann, Stav Chockler, Hana Kelly, David A. |
| contents | Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the existing tool ReX, and demonstrate that it is superior to other black-box XAI tools on a large-scale benchmark. Specifically, B-ReX achieves a Jensen-Shannon divergence of 0.072 $\pm$ 0.012 on random 10-valued Boolean formulae |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae Armoni-Friedmann, Stav Chockler, Hana Kelly, David A. Artificial Intelligence I.2.4 Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the existing tool ReX, and demonstrate that it is superior to other black-box XAI tools on a large-scale benchmark. Specifically, B-ReX achieves a Jensen-Shannon divergence of 0.072 $\pm$ 0.012 on random 10-valued Boolean formulae |
| title | Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae |
| topic | Artificial Intelligence I.2.4 |
| url | https://arxiv.org/abs/2509.09982 |