2.3k citations · 2.4k across the 19 of their papers we have counts for
22 papers
Interleaving Logic and Counting
Johan van Benthem, Thomas Icard
Reasoning with quantifier expressions in natural language combines logical and arithmetical features, transcending strict divides between qualitative and quantitative. Our topic is…
On Probabilistic and Causal Reasoning with Summation Operators
Duligur Ibeling, Thomas F. Icard, Milan Mossé
Ibeling et al. (2023). axiomatize increasingly expressive languages of causation and probability, and Mosse et al. (2024) show that reasoning (specifically the satisfiability probl…
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
Zhengxuan Wu, Atticus Geiger, Jing Huang +4
We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and cla…
Probing the Quantitative-Qualitative Divide in Probabilistic Reasoning
Duligur Ibeling, Thomas Icard, Krzysztof Mierzewski +1
This paper explores the space of (propositional) probabilistic logical languages, ranging from a purely `qualitative' comparative language to a highly `quantitative' language invol…
Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions
Duligur Ibeling, Thomas Icard
The aim of this paper is to make clear and precise the relationship between the Rubin causal model (RCM) and structural causal model (SCM) frameworks for causal inference. Adopting…
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
Atticus Geiger, Zhengxuan Wu, Christopher Potts +2
Causal abstraction is a promising theoretical framework for explainable artificial intelligence that defines when an interpretable high-level causal model is a faithful simplificat…
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Atticus Geiger, Duligur Ibeling, Amir Zur +8
Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications…
Causal Abstraction with Soft Interventions
Riccardo Massidda, Atticus Geiger, Thomas Icard +1
Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail. Existing theoretical proposals limit the anal…
A Completeness Result for Inequational Reasoning in a Full Higher-Order Setting
Lawrence S. Moss, Thomas F. Icard
This paper obtains a completeness result for inequational reasoning with applicative terms without variables in a setting where the intended semantic models are the full structures…
Causal Distillation for Language Models
Zhengxuan Wu, Atticus Geiger, Josh Rozner +5
Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student mo…
Inducing Causal Structure for Interpretable Neural Networks
Atticus Geiger, Zhengxuan Wu, Hanson Lu +5
In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashio…
Is Causal Reasoning Harder than Probabilistic Reasoning?
Milan Mossé, Duligur Ibeling, Thomas Icard
Many tasks in statistical and causal inference can be construed as problems of \emph{entailment} in a suitable formal language. We ask whether those problems are more difficult, fr…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
A Topological Perspective on Causal Inference
Duligur Ibeling, Thomas Icard
This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SC…
Causal Abstractions of Neural Networks
Atticus Geiger, Hanson Lu, Thomas Icard +1
Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method ground…
Preferential Structures for Comparative Probabilistic Reasoning
Matthew Harrison-Trainor, Wesley H. Holliday, Thomas F. Icard
Qualitative and quantitative approaches to reasoning about uncertainty can lead to different logical systems for formalizing such reasoning, even when the language for expressing u…
Provability and interpretability logics with restricted realizations
Thomas F. Icard, Joost J. Joosten
The provability logic of a theory T is the set of modal formulas, which under any arithmetical realization are provable in T . We slightly modify this notion by requiring the arith…
Intention as Commitment toward Time
Marc van Zee, Dragan Doder, Leendert van der Torre +3
In this paper we address the interplay among intention, time, and belief in dynamic environments. The first contribution is a logic for reasoning about intention, time and belief,…
Probabilistic Reasoning across the Causal Hierarchy
Duligur Ibeling, Thomas Icard
We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages. Our languages are of…
On Open-Universe Causal Reasoning
Duligur Ibeling, Thomas Icard
We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces. This enables a semantics for conditionals founded on a calculus…
On the Conditional Logic of Simulation Models
Duligur Ibeling, Thomas Icard
We propose analyzing conditional reasoning by appeal to a notion of intervention on a simulation program, formalizing and subsuming a number of approaches to conditional thinking i…
Indicative Conditionals and Dynamic Epistemic Logic
Wesley H. Holliday, Thomas F. Icard
Recent ideas about epistemic modals and indicative conditionals in formal semantics have significant overlap with ideas in modal logic and dynamic epistemic logic. The purpose of t…