Confident AI

2022/02/12 by Davis, Jim · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2202.05957

Abstract

In this paper, we propose "Confident AI" as a means to designing Artificial Intelligence (AI) and Machine Learning (ML) systems with both algorithm and user confidence in model predictions and reported results. The 4 basic tenets of Confident AI are Repeatability, Believability, Sufficiency, and Adaptability. Each of the tenets is used to explore fundamental issues in current AI/ML systems and together provide an overall approach to Confident AI.

Cited by

• Flowchart2Mermaid: A Vision-Language Model Powered System for Converting Flowcharts into Editable Diagram Code
• Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
• Enterprise Large Language Model Evaluation Benchmark

Related

• Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence
• Trustworthy AI
• Know Your Model (KYM): Increasing Trust in AI and Machine Learning
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• Towards Verified Artificial Intelligence