From Evidence to Decision: Exploring Evaluative AI
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_ | 1866915464518565888 |
|---|---|
| author | Le, Thao Miller, Tim Sonenberg, Liz Singh, Ronal Soyer, H. Peter |
| author_facet | Le, Thao Miller, Tim Sonenberg, Liz Singh, Ronal Soyer, H. Peter |
| contents | This paper presents a hypothesis-driven approach to improve AI-supported decision-making that is based on the Evaluative AI paradigm - a conceptual framework that proposes providing users with evidence for or against a given hypothesis. We propose an implementation of Evaluative AI by extending the Weight of Evidence framework, leading to hypothesis-driven models that support both tabular and image data. We demonstrate the application of the new decision-support approach in two domains: housing price prediction and skin cancer diagnosis. The findings show promising results in improving human decisions, as well as providing insights on the strengths and weaknesses of different decision-support approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01292 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Evidence to Decision: Exploring Evaluative AI Le, Thao Miller, Tim Sonenberg, Liz Singh, Ronal Soyer, H. Peter Artificial Intelligence Human-Computer Interaction This paper presents a hypothesis-driven approach to improve AI-supported decision-making that is based on the Evaluative AI paradigm - a conceptual framework that proposes providing users with evidence for or against a given hypothesis. We propose an implementation of Evaluative AI by extending the Weight of Evidence framework, leading to hypothesis-driven models that support both tabular and image data. We demonstrate the application of the new decision-support approach in two domains: housing price prediction and skin cancer diagnosis. The findings show promising results in improving human decisions, as well as providing insights on the strengths and weaknesses of different decision-support approaches. |
| title | From Evidence to Decision: Exploring Evaluative AI |
| topic | Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2402.01292 |