A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligence

TL;DR

A systematic review of the literature on evaluation criteria for Trustworthy Artificial Intelligence (TAI), with a focus on the seven EU principles of TAI, proposes a new classification system for each principle.

Abstract

This paper presents a systematic review of the literature on evaluation criteria for Trustworthy Artificial Intelligence (TAI), with a focus on the seven EU principles of TAI. This systematic literature review identifies and analyses current evaluation criteria, maps them to the EU TAI principles and proposes a new classification system for each principle. The findings reveal both a need for and significant barriers to standardising criteria for TAI evaluation. The proposed classification contributes to the development, selection and standardization of evaluation criteria for TAI governance.

Figures (5)

• Figure 1: Search String
• Figure 2: Number of Publications Per Year
• Figure 3: Types of publications
• Figure 4: Proposed classification for evaluation criteria for Trustworthy AI
• Figure 5: Proposed classification for fairness evaluation criteria