Showing stat.MLShow all
2 papers · 1 filter
stat.ML2025
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald +1
We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "eas…
stat.ML2025
What is causal about causal models and representations?
Frederik Hytting Jørgensen, Luigi Gresele, Sebastian Weichwald
Causal Bayesian networks are 'causal' models since they make predictions about interventional distributions. To connect such causal model predictions to real-world outcomes, we mus…