Principles of Human-Centered Design for Explainable AI

Human-centered design (HCD) makes AI explanations and interfaces clear, useful, accurate, and fair for the people who use them. Three principles:

1. Design for amplified decision-makingCopy Anchor Link

Supports people making high-stakes decisions under stress or pressure, maximizing the benefit of the technology while minimizing errors.

Key aspects: clarity, simplicity, usability, reflexivity (prompting users to reflect on their decisions), and accountability.

2. Design for unbiased decision-makingCopy Anchor Link

Keeps decision processes and tools free of bias:

1. Identify and assess potential biases.
2. Design transparent, fair processes and tools.
3. Train decision-makers to recognize and reduce bias.

Key aspects: transparency, fairness, training.

3. Design for human and AI learningCopy Anchor Link

Creates learning environments that work for both people and AI.

Key aspects:

• Cognitive apprenticeship: AI learns from human experts, the way apprentices learn from mentors.
• Personalization: learning adapted to each learner.
• User-centered design: accessible to everyone, including people with disabilities or language barriers.

RLHFCopy Anchor Link

Reinforcement learning from human feedback (RLHF) puts human feedback into the reward function so the model aligns with human goals. It improves performance and user satisfaction, and it's used in both traditional and generative AI.

Amazon SageMaker Ground Truth provides human-in-the-loop labeling, including RLHF: annotators rank or classify model responses, and that comparison and ranking data becomes the reward model.