Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills
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_ | 1866917960497496064 |
|---|---|
| author | Buçinca, Zana Swaroop, Siddharth Paluch, Amanda E. Doshi-Velez, Finale Gajos, Krzysztof Z. |
| author_facet | Buçinca, Zana Swaroop, Siddharth Paluch, Amanda E. Doshi-Velez, Finale Gajos, Krzysztof Z. |
| contents | People's decision-making abilities often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations. We argue this is partly because people intuitively seek contrastive explanations, which clarify the difference between the AI's decision and their own reasoning, while most AI systems offer "unilateral" explanations that justify the AI's decision but do not account for users' thinking. To align human-AI knowledge on decision tasks, we introduce a framework for generating human-centered contrastive explanations that explain the difference between AI's choice and a predicted, likely human choice about the same task. Results from a large-scale experiment (N = 628) demonstrate that contrastive explanations significantly enhance users' independent decision-making skills compared to unilateral explanations, without sacrificing decision accuracy. Amid rising deskilling concerns, our research demonstrates that incorporating human reasoning into AI design can foster human skill development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04253 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills Buçinca, Zana Swaroop, Siddharth Paluch, Amanda E. Doshi-Velez, Finale Gajos, Krzysztof Z. Human-Computer Interaction Artificial Intelligence People's decision-making abilities often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations. We argue this is partly because people intuitively seek contrastive explanations, which clarify the difference between the AI's decision and their own reasoning, while most AI systems offer "unilateral" explanations that justify the AI's decision but do not account for users' thinking. To align human-AI knowledge on decision tasks, we introduce a framework for generating human-centered contrastive explanations that explain the difference between AI's choice and a predicted, likely human choice about the same task. Results from a large-scale experiment (N = 628) demonstrate that contrastive explanations significantly enhance users' independent decision-making skills compared to unilateral explanations, without sacrificing decision accuracy. Amid rising deskilling concerns, our research demonstrates that incorporating human reasoning into AI design can foster human skill development. |
| title | Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2410.04253 |