Sign in

Angie Boggust

@angieboggust.bsky.social
432 followers 250 following 11 posts

MIT PhD candidate in the VIS group working on interpretability and human-AI alignment

PostsRepliesMedia
Reposted by Angie Boggust
VISxAI @visxai.bsky.social · 07/05/2025
#VISxAI IS BACK!! 🤖📊 Submit your interactive “explainables” and “explorables” that visualize, interpret, and explain AI. #IEEEVIS 📆 Deadline: July 30, 2025 visxai.io
visxai.io
Workshop on Visualization for AI Explainability
The role of visualization in artificial intelligence (AI) gained significant attention in recent years. With the growing complexity of AI models, the critical need for understanding their inner-workin...
094
Angie Boggust @angieboggust.bsky.social · 24/04/2025
I’ll be at #CHI2025 🌸 If you are excited about interpretability and human-AI alignment — let’s chat! And come see Abstraction Alignment ⬇️ in the Explainable AI paper session on Monday at 4:20 JST
050
Angie Boggust @angieboggust.bsky.social · 14/04/2025
#CHI2025 paper on human–AI alignment!🧵 Models can learn the right concepts but still be wrong in how they relate them. ✨Abstraction Alignment✨evaluates whether models learn human-aligned conceptual relationships. It reveals misalignments in LLMs💬 and medical datasets🏥. 🔗 arxiv.org/abs/2407.12543
An overview of Abstraction Alignment, including its authors and links to the paper, demo, and code.
190