Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects
This work addresses the challenge for AI/ML developers in balancing competing ethics aspects like fairness and privacy, though it is incremental as it compiles existing knowledge.
The paper identifies and catalogs 10 notable tensions and trade-offs between ethics principles in responsible AI, such as accuracy versus explainability, to help developers navigate these conflicts.
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.