solution 0The researchers conducted two sets of experiments ("Predict the speed-dating outcomes and get up to $6 (takes less than 20 min)" and a similar Prolific experiment) in which participants interacted with the AI system in a task of predicting the outcome of a dating to explore the impact of model explainability and feedback on user trust in AI and prediction accuracy. The results show that although explainability (e.g., global and local interpretation) does not significantly improve trust, feedback can most consistently and significantly improve behavioral trust. However, increased trust does not necessarily lead to the same level of performance gains, i.e., there is a "trust-performance paradox". Exploratory analysis reveals the mechanisms behind this phenomenon.
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study | Xue Zhirong's knowledge base
summary
Problem finding
blog
The results show that feedback has a more significant impact on improving users' trust in AI than explainability, but this enhanced trust does not lead to a corresponding performance improvement. Further exploration suggests that feedback induces users to over-trust (i.e., accept the AI's suggestions when it is wrong) or distrust (ignore the AI's suggestions when it is correct), which may negate the benefits of increased trust, leading to a "trust-performance paradox". The researchers call for future research to focus on how to design strategies to ensure that explanations foster appropriate trust to improve the efficiency of human-robot collaboration.
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
A1: According to research, feedback (e.g. result output) is a key factor influencing user trust. It is the most significant and reliable way to increase user trust in AI behavior.
tool
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
Draw inferences
Q3: How does result feedback and model interpretability affect user task performance?
To assess trust more accurately, the researchers used behavioral trust (WoA), a measure that takes into account the difference between the user's predictions and the AI's recommendations, and is independent of the model's accuracy. By comparing WoA under different conditions, researchers can analyze the relationship between trust and performance.
User experience
Interview
Personal insights
outcome
speech
Draw inferences
artificial intelligence
summary
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
Q1: How does feedback affect users' trust in AI?
Interactive
To assess trust more accurately, the researchers used behavioral trust (WoA), a measure that takes into account the difference between the user's predictions and the AI's recommendations, and is independent of the model's accuracy. By comparing WoA under different conditions, researchers can analyze the relationship between trust and performance.
The results show that feedback has a more significant impact on improving users' trust in AI than explainability, but this enhanced trust does not lead to a corresponding performance improvement. Further exploration suggests that feedback induces users to over-trust (i.e., accept the AI's suggestions when it is wrong) or distrust (ignore the AI's suggestions when it is correct), which may negate the benefits of increased trust, leading to a "trust-performance paradox". The researchers call for future research to focus on how to design strategies to ensure that explanations foster appropriate trust to improve the efficiency of human-robot collaboration.
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
outcome
Xue Zhirong, Designer, Interaction Design, Human-Computer Interaction, Artificial Intelligence, Official Website, Blog, Creator, Author, Engineer, Paper, Product Design, Research, AI, HCI, Design, Learning, Knowledge Base, xuezhirong, UX, Design, Research, AI, HCI, Designer, Engineer, Author, Blog, Papers, Product Design, Study, Learning, User Experience
User experience
Q3: How does result feedback and model interpretability affect user task performance?
Problem finding
To assess trust more accurately, the researchers used behavioral trust (WoA), a measure that takes into account the difference between the user's predictions and the AI's recommendations, and is independent of the model's accuracy. By comparing WoA under different conditions, researchers can analyze the relationship between trust and performance.
Personal insights
artificial intelligenceyuzhibolangzi@gmail.com Interactive