Actionable AI: Enabling Non Experts to Understand and Configure AI Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929751029972992 |
|---|---|
| author | Boulard, Cécile Viswanathan, Sruthi Fey, Wanda Jacquin, Thierry |
| author_facet | Boulard, Cécile Viswanathan, Sruthi Fey, Wanda Jacquin, Thierry |
| contents | Interaction between humans and AI systems raises the question of how people understand AI systems. This has been addressed with explainable AI, the interpretability arising from users' domain expertise, or collaborating with AI in a stable environment. In the absence of these elements, we discuss designing Actionable AI, which allows non-experts to configure black-box agents. In this paper, we experiment with an AI-powered cartpole game and observe 22 pairs of participants to configure it via direct manipulation. Our findings suggest that, in uncertain conditions, non-experts were able to achieve good levels of performance. By influencing the behaviour of the agent, they exhibited an operational understanding of it, which proved sufficient to reach their goals. Based on this, we derive implications for designing Actionable AI systems. In conclusion, we propose Actionable AI as a way to open access to AI-based agents, giving end users the agency to influence such agents towards their own goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Actionable AI: Enabling Non Experts to Understand and Configure AI Systems Boulard, Cécile Viswanathan, Sruthi Fey, Wanda Jacquin, Thierry Human-Computer Interaction Artificial Intelligence Interaction between humans and AI systems raises the question of how people understand AI systems. This has been addressed with explainable AI, the interpretability arising from users' domain expertise, or collaborating with AI in a stable environment. In the absence of these elements, we discuss designing Actionable AI, which allows non-experts to configure black-box agents. In this paper, we experiment with an AI-powered cartpole game and observe 22 pairs of participants to configure it via direct manipulation. Our findings suggest that, in uncertain conditions, non-experts were able to achieve good levels of performance. By influencing the behaviour of the agent, they exhibited an operational understanding of it, which proved sufficient to reach their goals. Based on this, we derive implications for designing Actionable AI systems. In conclusion, we propose Actionable AI as a way to open access to AI-based agents, giving end users the agency to influence such agents towards their own goals. |
| title | Actionable AI: Enabling Non Experts to Understand and Configure AI Systems |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2503.06803 |