Reposted by DTAI - KU Leuven
🚨 Can we trust that the “concepts” in concept-based models actually mean what we think they mean?
Our new work, Prototype-Grounded Concept Models (PGCMs), makes concept alignment directly inspectable and correctable. #ICML26
Paper: arxiv.org/abs/2604.16076 🧵 (1/5)
