Conference 0The 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 | Xue Zhirong's knowledge base
solution
Dissertation Summary
Problem finding
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.
Interactive
thesis
MIT Licensed | Copyright © 2024-present Zhirong Xue's knowledge base
Xue Zhirong is a designer, engineer, and author of several books; Founder of the Design Open Source Community, Co-founder of MiX Copilot; Committed to making the world a better place with design and technology. This knowledge base will update AI, HCI and other content, including news, papers, presentations, sharing, etc.
The 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 content is made up of:
The researchers found that although it is generally believed that the interpretability of the model can help improve the user's trust in the AI system, in the actual experiment, the global and local interpretability does not lead to a stable and significant trust improvement. Conversely, feedback (i.e., the output of the results) has a more significant effect on increasing user trust in the AI. However, this increased trust does not directly translate into an equivalent improvement in performance.
Xue Zhirong's knowledge base
Robots and digital humans
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.
artificial intelligence
Q1: How does feedback affect users' trust in AI?
Q2: Does explainability necessarily enhance users' trust in AI?
A2: Although it is generally believed that the explanatory nature of the model helps to improve user trust, the experimental results show that this enhancement is not significant and not as effective as feedback. In specific cases, such as areas of low expertise, some form of interpretation may result in only a modest increase in appropriate trust.
A3: The study found that the feedback of the results can improve the accuracy of the user's predictions (reducing the absolute error), thereby improving the performance of working with AI. However, interpretability does not have as much impact on user task performance as it does on trust. This may mean that we should pay more attention to how to effectively use feedback mechanisms to improve the usefulness and effectiveness of AI-assisted decision-making.
A3: The study found that the feedback of the results can improve the accuracy of the user's predictions (reducing the absolute error), thereby improving the performance of working with AI. However, interpretability does not have as much impact on user task performance as it does on trust. This may mean that we should pay more attention to how to effectively use feedback mechanisms to improve the usefulness and effectiveness of AI-assisted decision-making.
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
About me
Original address:
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.
Personal insights
Based on large language model generation, there may be a risk of errors.
User experience