茶杯狐Cupfox
本站设置于美国加州湾区以服务海外华人同胞,所有视频和图片均来自互联网收集而来,版权归原创者所有,本网站只提供web页面服务,并不提供资源存储,也不参与录制、上传。
Xue Zhirong's knowledge base
Draw inferences
tool
Q3: How does result feedback and model interpretability affect user task performance?
outcome
Personal insights
interview
Interview
summary
About me
Interactive
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
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.
MIT Licensed | Copyright © 2024-present Zhirong Xue's knowledge base
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.
Conference
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
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
artificial intelligence
speech
Translation
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.
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.
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study | Xue Zhirong'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.
Q1: How does feedback affect users' trust in AI?
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.
The Interpretability of Artificial Intelligence and the Impact of Outcome Feedback on Trust: A Comparative Study
solution
Problem finding
语言
繁體
简体
英语
最近更新
全部电影
大夏剑主 第126集 线上看
(
...
)
回到《
大夏剑主
》列表
大夏剑主
第125集
大夏剑主
第127集
Q2: Does explainability necessarily enhance users' trust in AI?
Original address:
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.
Robots and digital humans
B
《大梦归离》:捉妖小队正式成立!人物关系错综复杂
看暗黑超英大片《毒液:最后一舞》,你必须要知道的十大知识点
《我的差评女友》即将上线,邢昭林卢洋洋甜蜜热恋!
闫妮蒋欣配一脸,邻居处成姐妹,你迷上小巷人家的理由是什么?
《乔妍的心事》口碑出炉!剧情平淡题材不明,赵丽颖演技遭遇差评
《大梦归离》首播,没啥故事,絮叨磨叽,催眠神剧,郭敬明神逻辑
《惊天大营救》上映,托尼·贾好似核动力猛兽,从头狂暴打到尾
断层第一,争议漫天,这尺度新片直接爆了
《小巷人家》原著:黄玲的反抗,庄图南不理解,好在还有庄筱婷
最近更新
画江湖之不良人7 更新至03集
blog
火凤燎原第二季 更新至13集
blog
永恒剑祖 更新至33集
blog
武炼巅峰 更新至43集
blog
大夏剑主 更新至180集
blog
无尽神域 更新至69集
blog
陆地键仙 更新至105集
blog
师兄啊师兄 更新至83集
blog
万古神话 更新至278集
blog
武逆 更新至28集
blog
仙武帝尊 更新至437集
blog
万界至尊 更新至205集
blog
完美世界 更新至209集
blog
念无双 更新至20集
blog
师兄啊师兄第二季 更新至83集
blog
玄帝传说 更新至158集
神印王座 更新至153集
君子无疾 更新至09集
天渊归来:我即是天灾动态漫画 更新至75集
剑道第一仙 更新至112集
天命大主宰 更新至28集
我能无限顿悟 更新至49集
都市古仙医 更新至58集
一世独尊 更新至111集
遮天 更新至103集
武逆2024 更新至28集
斗罗大陆5重生唐三 更新至13集
开局我长生,结局我无敌 更新至64集
为师的爱徒人设,千万不能崩! 更新至87集
收徒亿万返还:为师无敌世间 更新至117集
末世超级系统 更新至271集
弟子修炼,我躺平!第二季 更新至58集
暴富系统:我有999个新马甲 更新至106集
气运之子:我可以无限暴击 更新至82集
Based on large language model generation, there may be a risk of errors.
原来我早就无敌了动态漫 更新至144集
长生不死的我只修禁术 更新至64集
氪丹修仙只苟长生 更新至50集
仙帝入侵第二季 更新至39集
女魔王说我太强了 更新至75集
统计代码
УкраїнськаName
Norge
color name
nederlands
しろうと
Pilipino
English
ກະຣຸນາ
తెలుగుQFontDatabase
Română
नेपालीName
Français
Kreyòl ayisyen
český
Svenska
Русский язык
Malagasy
ဗာရမ်
پښتوName
คนไทย
Արմենյան
简体中文
Persian
繁體中文
Kurdî
Türkçe
हिन्दी
български
Malay
Kiswahili
ଓଡିଆ
ÍslandName
Íris
ខ្មែរKCharselect unicode block name
ગુજરાતી
Slovenská
ಕನ್ನಡ್Name
היברית
magyar
मराठीName
தாமில்
eesti keel
മലമാലം
ᐃᓄᒃᑎᑐᑦ
بالعربية
Deutsch
slovenščina
বেঙ্গালী
اوردو
azerbaijani
português
lifiava
afrikaans
汤加语
ελληνικά
IndonesiaName
Español
dansk
amharic
ਪੰਜਾਬੀName
albanian
Lietuva
italiano
Tiếng Việt
한국어
Malti
suomi
català
hrvatski
bosnian
Polski
latviešu
Maori