Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909307099938816 |
|---|---|
| author | Sanderson, Conrad Douglas, David Lu, Qinghua |
| author_facet | Sanderson, Conrad Douglas, David Lu, Qinghua |
| contents | Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_08275 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects Sanderson, Conrad Douglas, David Lu, Qinghua Computers and Society Artificial Intelligence 68T01, 68T10 K.4.0; I.2.m; D.2.10; C.4 Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML systems. |
| title | Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects |
| topic | Computers and Society Artificial Intelligence 68T01, 68T10 K.4.0; I.2.m; D.2.10; C.4 |
| url | https://arxiv.org/abs/2304.08275 |