• Skip to main content
  • Skip to primary sidebar
  • Skip to footer
  • Core Principles of Responsible AI
    • Accountability
    • Fairness
    • Privacy
    • Safety and Security
    • Sustainability
    • Transparency
  • Special Topics
    • AI in Industry
    • Ethical Implications
    • Human-Centered Design
    • Regulatory Landscape
    • Technical Methods
  • Living Dictionary
  • State of AI Ethics
  • AI Ethics Brief
  • 🇫🇷
Montreal AI Ethics Institute

Montreal AI Ethics Institute

Democratizing AI ethics literacy

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

September 21, 2023

🔬 Research Summary by Min Lee, an Assistant Professor in Computer Science at Singapore Management University, where he creates and evaluates interactive, human-centered AI systems for societal problems (e.g. health).

[Original paper by Min Hun Lee and Chong Jun Chew]


Overview: Although advanced artificial intelligence (AI) and machine learning (ML) models are increasingly being explored to assist various decision-making tasks (e.g., health, bail decisions), users might place too much trust even with ‘wrong’ AI outputs. This paper explores the effect of counterfactual explanations on users’ trust and reliance on AI during a clinical decision-making task.


Introduction

Advanced artificial intelligence (AI) and machine learning (ML) models are increasingly being considered to increase efficiency and reduce the cost of performing decision-making tasks from various types of organizations and domains (e.g., health, bail decisions, child welfare services, etc.). However, users might place too much trust in the AI/ML system and even agree with ‘wrong’ AI outputs, and they achieve worse performance than humans or AI/ML models alone.

Key Insights

What did we do? 

In this work, we contribute to an empirical study that analyzes the effect of AI explanations on users’ trust and reliance on AI during clinical decision-making. Specifically, we focus on the task of assessing post-stroke survivors’ quality of motion. We conducted a within-subject experiment with seven therapists and ten laypersons to compare the effect of counterfactual explanations with one of the widely used AI explanations, feature importance explanations.

  • Feature importance: describes the contribution/importance of each input feature (e.g., kinematic variables — joint angle, distance between joints for the context of the study)
  • Counterfactual explanations: describe how the inputs can be modified to achieve an AI output in a certain way (e.g., how does a patient’s incorrect/abnormal motion need to be changed to become a normal motion?)

One potential reason for overreliance on AI might be that humans rarely involve analytical thinking on AI outputs. This work hypothesizes that reviewing counterfactual explanations will allow a user to think critically about changing AI inputs to update an AI output and improve the user’s analytical review of an AI output to reduce overreliance on AI.

What did we learn?

  • When ‘right’ AI outputs were presented, human+AI performance with both feature importance and counterfactual explanations increased than humans alone
  • When ‘wrong’ AI outputs were presented, human+AI performance with both feature importance and counterfactual explanations decreased than humans alone
  • Counterfactual explanations reduced overreliance on ‘wrong’ AI outputs by 21% compared to feature importance
  • Domain experts (i.e., therapists) had lower performance degradation and overreliance on ‘wrong’ AI outputs than laypersons while using both feature importance and counterfactual explanations
  • Both experts and laypersons expressed higher subjective usability scores of ‘usefulness,’ ‘less effort & frustration,’ ‘trust,’ and ‘usage intent’ on feature importance than counterfactual explanations.

Between the lines

Implications: Our work shows that providing AI explanations does not necessarily indicate improved human-AI collaborative decision-making. This work provides new insights into:

1) the potential of counterfactual explanations to improve analytical reviews on AI outputs and reduce overreliance on ‘wrong’ AI outputs with the cost of cognitive burdens.

2) a gap between users’ perceived benefits and actual trustworthiness/usefulness of an AI system (e.g., improving performance while relying on ‘right’ outcomes)

Please check our paper for the details of this work (link). If you are interested in further discussing this work or collaborating in this space, please contact Min Lee (link).

Citation Format: Min Hun Lee and Chong Jun Chew. 2023. Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making. Proc. ACM Hum.-Comput. Interact. 7, CSCW2, Article 369 (October 2023), 22 pages. https://doi.org/10.1145/3610218

Want quick summaries of the latest research & reporting in AI ethics delivered to your inbox? Subscribe to the AI Ethics Brief. We publish bi-weekly.

Primary Sidebar

🔍 SEARCH

Spotlight

Canada’s Minister of AI and Digital Innovation is a Historic First. Here’s What We Recommend.

Am I Literate? Redefining Literacy in the Age of Artificial Intelligence

AI Policy Corner: The Texas Responsible AI Governance Act

AI Policy Corner: Singapore’s National AI Strategy 2.0

AI Governance in a Competitive World: Balancing Innovation, Regulation and Ethics | Point Zero Forum 2025

related posts

  • The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks (Research Summa...

    The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks (Research Summa...

  • LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games

    LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games

  • DICES Dataset: Diversity in Conversational AI Evaluation for Safety

    DICES Dataset: Diversity in Conversational AI Evaluation for Safety

  • The Values Encoded in Machine Learning Research

    The Values Encoded in Machine Learning Research

  • The GPTJudge: Justice in a Generative AI World

    The GPTJudge: Justice in a Generative AI World

  • AI Has Arrived in Healthcare, but What Does This Mean?

    AI Has Arrived in Healthcare, but What Does This Mean?

  • Risk and Trust Perceptions of the Public of Artificial Intelligence Applications

    Risk and Trust Perceptions of the Public of Artificial Intelligence Applications

  • Design Principles for User Interfaces in AI-Based Decision Support Systems: The Case of Explainable ...

    Design Principles for User Interfaces in AI-Based Decision Support Systems: The Case of Explainable ...

  • A Hazard Analysis Framework for Code Synthesis Large Language Models

    A Hazard Analysis Framework for Code Synthesis Large Language Models

  • Private Training Set Inspection in MLaaS

    Private Training Set Inspection in MLaaS

Partners

  •  
    U.S. Artificial Intelligence Safety Institute Consortium (AISIC) at NIST

  • Partnership on AI

  • The LF AI & Data Foundation

  • The AI Alliance

Footer

Categories


• Blog
• Research Summaries
• Columns
• Core Principles of Responsible AI
• Special Topics

Signature Content


• The State Of AI Ethics

• The Living Dictionary

• The AI Ethics Brief

Learn More


• About

• Open Access Policy

• Contributions Policy

• Editorial Stance on AI Tools

• Press

• Donate

• Contact

The AI Ethics Brief (bi-weekly newsletter)

About Us


Founded in 2018, the Montreal AI Ethics Institute (MAIEI) is an international non-profit organization equipping citizens concerned about artificial intelligence and its impact on society to take action.


Archive

  • © MONTREAL AI ETHICS INSTITUTE. All rights reserved 2024.
  • This work is licensed under a Creative Commons Attribution 4.0 International License.
  • Learn more about our open access policy here.
  • Creative Commons License

    Save hours of work and stay on top of Responsible AI research and reporting with our bi-weekly email newsletter.