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
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.
Personal insights
thesis
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
blog
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.
outcome
summary
Q3: How does result feedback and model interpretability affect user task performance?
About me summary
English
var maccms={"path":"","mid":"1","aid":"14","url":"www.rejune.com","wapurl":"www.rejune.com","mob_status":"0"};
Bahasa Indonesia
var _hmt = _hmt || []; (function () { var hm = document.createElement("script"); hm.src ="https://hm.baidu.com/hm.js?4f2c9b6c4700a255e81f0d2c017c664d"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); (function () { var bp = document.createElement('script'); var curProtocol = window.location.protocol.split(':')[0]; if (curProtocol === 'https') { bp.src = 'https://zz.bdstatic.com/linksubmit/push.js'; } else { bp.src = 'http://push.zhanzhang.baidu.com/push.js'; } var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(bp, s); })();
translate.service.use("client.edge"); translate.setAutoDiscriminateLocalLanguage(); translate.listener.start(); translate.selectLanguageTag.show=false; translate.execute();$("#languageToggle").on("click",function(){$(".languagemenu_container").toggle()});$(".languagemenu_item").on("click",function(){translate.changeLanguage($(this).data("lang")); localStorage.setItem("lang",$(this).data("lang"));$(".languagemenu_container").hide()});
TAG：
if ('serviceWorker' in navigator) { window.addEventListener('load', () => { navigator.serviceWorker.register('/template/shoutu42/assets/app/service-worker.js') .then(registration => { console.log('Service Worker registered:', registration); }) .catch(error => { console.log('Service Worker registration failed:', error); }); }); }
artificial intelligence
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.
outcome
About me
Based on large language model generation, there may be a risk of errors.

Interview

Based on large language model generation, there may be a risk of errors.
summary

Interview

summary
Based on large language model generation, there may be a risk of errors.

Q1: How does feedback affect users' trust in AI?

Based on large language model generation, there may be a risk of errors.
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.

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.

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.
Translation

Interview

Translation
Based on large language model generation, there may be a risk of errors.

Q2: Does explainability necessarily enhance users' trust in AI?

Based on large language model generation, there may be a risk of errors.
Xue Zhirong's knowledge base

Q1: How does feedback affect users' trust in AI?

Xue Zhirong's knowledge base
About me

Interview

About me
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.

Interview

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.
Q2: Does explainability necessarily enhance users' trust in AI?

Interview

Q2: Does explainability necessarily enhance users' trust in AI?
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.

Interview

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.

Interview

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.
Q3: How does result feedback and model interpretability affect user task performance?
About me
thesis
speech

Conference

English
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.
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
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
interview
interview
Conference
Conference
Conference
Conference

MIT Licensed | Copyright © 2024-present Zhirong Xue's knowledge base