Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence

06/06/2022
by   Thao Le, et al.
0

In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can help build trust between humans and AI systems. However, most existing research only used the confidence score as a form of communication, and we still lack ways to explain why the algorithm is confident. This paper also presents two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2023

Explaining Model Confidence Using Counterfactuals

Displaying confidence scores in human-AI interaction has been shown to h...
research
08/08/2023

Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making

Artificial intelligence (AI) is increasingly being considered to assist ...
research
04/21/2022

Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI

Counterfactual explanations are increasingly used to address interpretab...
research
05/25/2022

Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI

Evaluating an explanation's faithfulness is desired for many reasons suc...
research
04/27/2023

Why not both? Complementing explanations with uncertainty, and the role of self-confidence in Human-AI collaboration

AI and ML models have already found many applications in critical domain...
research
09/21/2021

Interpretable Directed Diversity: Leveraging Model Explanations for Iterative Crowd Ideation

Feedback can help crowdworkers to improve their ideations. However, curr...
research
05/30/2018

To Trust Or Not To Trust A Classifier

Knowing when a classifier's prediction can be trusted is useful in many ...

Please sign up or login with your details

Forgot password? Click here to reset