Concept-based Explainable Artificial Intelligence: A Survey
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918194602573824 |
|---|---|
| author | Poeta, Eleonora Ciravegna, Gabriele Pastor, Eliana Cerquitelli, Tania Baralis, Elena |
| author_facet | Poeta, Eleonora Ciravegna, Gabriele Pastor, Eliana Cerquitelli, Tania Baralis, Elena |
| contents | The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been disputed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have arisen in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We define and identify different concepts and explanation types. We provide a taxonomy identifying nine categories and propose guidelines for selecting a suitable category based on the development context. Additionally, we report common evaluation strategies including metrics, human evaluations and dataset employed, aiming to assist the development of future methods. We believe this survey will serve researchers, practitioners, and domain experts in comprehending and advancing this innovative field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_12936 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Concept-based Explainable Artificial Intelligence: A Survey Poeta, Eleonora Ciravegna, Gabriele Pastor, Eliana Cerquitelli, Tania Baralis, Elena Artificial Intelligence Human-Computer Interaction The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been disputed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have arisen in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We define and identify different concepts and explanation types. We provide a taxonomy identifying nine categories and propose guidelines for selecting a suitable category based on the development context. Additionally, we report common evaluation strategies including metrics, human evaluations and dataset employed, aiming to assist the development of future methods. We believe this survey will serve researchers, practitioners, and domain experts in comprehending and advancing this innovative field. |
| title | Concept-based Explainable Artificial Intelligence: A Survey |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2312.12936 |