Rapid Trust Calibration through Interpretable and Uncertainty-Aware AI

Abstract Artificial intelligence (AI) systems hold great promise as decision-support tools, but we must be able to identify and understand their inevitable mistakes if they are to fulfil this potential. This is particularly true in do- mains where the decisions are high-stakes, such as law, medicine, and the military. In this Perspective, we describe the particular challenges for AI decision support posed in military coalition operations. These include having to deal with limited, low-quality data, which inevitably compromises AI performance. We suggest that these problems can be mitigated by taking steps that allow rapid trust calibration so that decision makers understand the AI system's limitations and likely failures and can calibrate their trust in its outputs appropriately. We propose that AI services can achieve this by being both interpretable and uncertainty- aware. Creating such AI systems poses various technical and human factors challenges. We review these challenges and recommend directions for future research.
  • Richard Tomsett (IBM UK)
  • Alun Preece (Cardiff)
  • Dave Braines (IBM UK)
  • Federico Cerutti (Cardiff)
  • Supriyo Chakraborty (IBM US)
  • Mani Srivastava (UCLA)
  • Gavin Pearson (Dstl)
  • Lance Kaplan (ARL)
Date Jul-2020
Venue CellPress Patterns, Vol 1 Issue 4 [link]