Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915250358452224 |
|---|---|
| author | Barbu, Eduard Domnich, Marharyta Vicente, Raul Sakkas, Nikos Morim, André |
| author_facet | Barbu, Eduard Domnich, Marharyta Vicente, Raul Sakkas, Nikos Morim, André |
| contents | This study presents insights gathered from surveys and discussions with specialists in three domains, aiming to find essential elements for a universal explanation framework that could be applied to these and other similar use cases. The insights are incorporated into a software tool that utilizes GP algorithms, known for their interpretability. The applications analyzed include a medical scenario (involving predictive ML), a retail use case (involving prescriptive ML), and an energy use case (also involving predictive ML). We interviewed professionals from each sector, transcribing their conversations for further analysis. Additionally, experts and non-experts in these fields filled out questionnaires designed to probe various dimensions of explanatory methods. The findings indicate a universal preference for sacrificing a degree of accuracy in favor of greater explainability. Additionally, we highlight the significance of feature importance and counterfactual explanations as critical components of such a framework. Our questionnaires are publicly available to facilitate the dissemination of knowledge in the field of XAI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11958 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis Barbu, Eduard Domnich, Marharyta Vicente, Raul Sakkas, Nikos Morim, André Machine Learning Human-Computer Interaction This study presents insights gathered from surveys and discussions with specialists in three domains, aiming to find essential elements for a universal explanation framework that could be applied to these and other similar use cases. The insights are incorporated into a software tool that utilizes GP algorithms, known for their interpretability. The applications analyzed include a medical scenario (involving predictive ML), a retail use case (involving prescriptive ML), and an energy use case (also involving predictive ML). We interviewed professionals from each sector, transcribing their conversations for further analysis. Additionally, experts and non-experts in these fields filled out questionnaires designed to probe various dimensions of explanatory methods. The findings indicate a universal preference for sacrificing a degree of accuracy in favor of greater explainability. Additionally, we highlight the significance of feature importance and counterfactual explanations as critical components of such a framework. Our questionnaires are publicly available to facilitate the dissemination of knowledge in the field of XAI. |
| title | Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2405.11958 |