Highlighting “what” AI systems can’t do is not enough to foster realistic mental models. It is imp to explain “why” AI systems can’t do certain things. Seamful XAI helps with that.
It was a joy working with @UpolEhsan, @QVeraLiao, @mark_riedl, and @haldaume3 on this CSCW paper.
All AI systems make mistakes.
🧐 What if users could leverage AI flaws to understand it & take informed actions?
🚀 Our #CSCW2024 paper on Seamful XAI offers a process to foresee, locate, & leverage AI flaws—boosting user understanding & agency.
But why should you care?⤵️
1/n
Y'all, I've been doing a series of posts about the RAI Maturity Model on LinkedIn https://t.co/EWuRHaACfz
Today: building a *common language* across disciplines so you can work together.
🚨 New pre-print alert! 🚨
Excited to share “The Who in Explainable AI: How AI Background Shapes Perceptions of AI Explanations”
w/ the amazing team: @samirpassi,@QVeraLiao,Larry Chan,Ethan Lee,@michael_muller,@mark_riedl
🔗https://t.co/rhP4h2OcGD
💡Findings at a glance...
1/n
The field of AI always seems in a rush to get somewhere, making it hard to find time to take stock. The Responsible AI Maturity Model can help orgs. do just that - pause; reflect on where they are, where they want to (+should) go, and why; and strategize about how to get there.
Examples of filtering technologies include blocklists, allowlists, rule-based systems, and classifiers. Filtering technologies can be used to mitigate a wide range of responsible AI issues such as offensive content, fairness issues, privacy concerns, and safety issues.
2/4