Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

16 February 2025

Papers citing "Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens"

2 / 2 papers shown

Title
If Concept Bottlenecks are the Question, are Foundation Models the Answer? Nicola Debole Pietro Barbiero Francesco Giannini Andrea Passerini Stefano Teso Emanuele Marconato 39 0 0 28 Apr 2025
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling Emanuele Marconato Sébastien Lachapelle Sebastian Weichwald Luigi Gresele 47 3 0 30 Oct 2024