Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2306.13935 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909170989531136 |
|---|---|
| author | Nguyen, Emma Thuong Ghose, Abhishek |
| author_facet | Nguyen, Emma Thuong Ghose, Abhishek |
| contents | Explainable AI (XAI) techniques have become popular for multiple use-cases in the past few years. Here we consider its use in studying model predictions to gather additional training data. We argue that this is equivalent to Active Learning, where the query strategy involves a human-in-the-loop. We provide a mathematical approximation for the role of the human, and present a general formalization of the end-to-end workflow. This enables us to rigorously compare this use with standard Active Learning algorithms, while allowing for extensions to the workflow. An added benefit is that their utility can be assessed via simulation instead of conducting expensive user-studies. We also present some initial promising results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_13935 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Are Good Explainers Secretly Human-in-the-Loop Active Learners? Nguyen, Emma Thuong Ghose, Abhishek Artificial Intelligence Explainable AI (XAI) techniques have become popular for multiple use-cases in the past few years. Here we consider its use in studying model predictions to gather additional training data. We argue that this is equivalent to Active Learning, where the query strategy involves a human-in-the-loop. We provide a mathematical approximation for the role of the human, and present a general formalization of the end-to-end workflow. This enables us to rigorously compare this use with standard Active Learning algorithms, while allowing for extensions to the workflow. An added benefit is that their utility can be assessed via simulation instead of conducting expensive user-studies. We also present some initial promising results. |
| title | Are Good Explainers Secretly Human-in-the-Loop Active Learners? |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2306.13935 |