This paper explores the space of (propositional) probabilistic logical
l...
The aim of this paper is to make clear and precise the relationship betw...
Causal abstraction is a promising theoretical framework for explainable
...
A faithful and interpretable explanation of an AI model's behavior and
i...
Causal abstraction provides a theory describing how several causal model...
Language models (LMs) are becoming the foundation for almost all major
l...
Distillation efforts have led to language models that are more compact a...
In many areas, we have well-founded insights about causal structure that...
Many tasks in statistical and causal inference can be construed as probl...
This paper presents a topological learning-theoretic perspective on caus...
Structural analysis methods (e.g., probing and feature attribution) are
...
In this paper we address the interplay among intention, time, and belief...
We propose a formalization of the three-tier causal hierarchy of associa...
We extend two kinds of causal models, structural equation models and
sim...
We propose analyzing conditional reasoning by appeal to a notion of
inte...