中文
相关论文

相关论文: From Probability to Counterfactuals: the Increasin…

200 篇论文

Pearl's Causal Hierarchy (PCH) is a central framework for reasoning about probabilistic, interventional, and counterfactual statements, yet the satisfiability problem for PCH formulas is computationally intractable in almost all classical…

人工智能 · 计算机科学 2026-01-27 Robert Ganian , Marlene Gründel , Simon Wietheger

We study the complexity of satisfiability problems in probabilistic and causal reasoning. Given random variables $X_1, X_2,\ldots$ over finite domains, the basic terms are probabilities of propositional formulas over atomic events $X_i =…

计算复杂性 · 计算机科学 2025-04-29 Markus Bläser , Julian Dörfler , Maciej Liśkiewicz , Benito van der Zander

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 strictly increasing expressivity, the first capable of…

计算机科学中的逻辑 · 计算机科学 2021-06-03 Duligur Ibeling , Thomas Icard

Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems. As in any other growing subfield, patience seems to be a virtue…

人工智能 · 计算机科学 2022-12-27 Matej Zečević , Moritz Willig , Devendra Singh Dhami , Kristian Kersting

We study formal languages which are capable of fully expressing quantitative probabilistic reasoning and do-calculus reasoning for causal effects, from a computational complexity perspective. We focus on satisfiability problems whose…

人工智能 · 计算机科学 2023-05-17 Benito van der Zander , Markus Bläser , Maciej Liśkiewicz

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, from a computational perspective, for \emph{causal}…

计算机科学中的逻辑 · 计算机科学 2023-06-02 Milan Mossé , Duligur Ibeling , Thomas Icard

Ibeling et al. (2023). axiomatize increasingly expressive languages of causation and probability, and Mosse et al. (2024) show that reasoning (specifically the satisfiability problem) in each causal language is as difficult, from a…

逻辑 · 数学 2024-05-21 Duligur Ibeling , Thomas F. Icard , Milan Mossé

Structural causal models are the basic modelling unit in Pearl's causal theory; in principle they allow us to solve counterfactuals, which are at the top rung of the ladder of causation. But they often contain latent variables that limit…

人工智能 · 计算机科学 2021-11-23 Marco Zaffalon , Alessandro Antonucci , Rafael Cabañas

In [4], we introduced an extension of team semantics (causal teams) which assigns an interpretation to interventionist counterfactuals and causal notions based on them (as e.g. in Pearl's and Woodward's manipulationist approaches to…

计算机科学中的逻辑 · 计算机科学 2023-05-23 Fausto Barbero , Gabriel Sandu

We introduce a formalism for the evaluation of counterfactual queries in the framework of quantum causal models, generalising Pearl's semantics for counterfactuals in classical causal models, thus completing the last rung in the quantum…

量子物理 · 物理学 2024-09-18 Ardra Kooderi Suresh , Markus Frembs , Eric G. Cavalcanti

Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence. Our…

机器学习 · 计算机科学 2026-03-20 Shruti Joshi , Aaron Mueller , David Klindt , Wieland Brendel , Patrik Reizinger , Dhanya Sridhar

Pearl's causal hierarchy has garnered sustained attention as a foundational lens for formulating and understanding causal questions, and has been extensively discussed within the framework of structural causal models. In this paper, we…

其他统计学 · 统计学 2026-01-29 Peng Wu , Linbo Wang

Counterfactual explanations (CEs) are methods for generating an alternative scenario that produces a different desirable outcome. For example, if a student is predicted to fail a course, then counterfactual explanations can provide the…

机器学习 · 统计学 2023-01-09 Bevan I. Smith

Counterfactual reasoning, a cornerstone of human cognition and decision-making, is often seen as the 'holy grail' of causal learning, with applications ranging from interpreting machine learning models to promoting algorithmic fairness.…

机器学习 · 计算机科学 2025-04-11 Yahya Aalaila , Gerrit Großmann , Sumantrak Mukherjee , Jonas Wahl , Sebastian Vollmer

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction. Yet,…

机器学习 · 计算机科学 2023-09-12 Wenbo Zhang , Tong Wu , Yunlong Wang , Yong Cai , Hengrui Cai

Counterfactual reasoning aims at answering contrary-to-fact questions like ``Would have Alice recovered had she taken aspirin?'' and corresponds to the most fine-grained layer of causation. Critically, while many counterfactual statements…

人工智能 · 计算机科学 2025-09-23 Lucas de Lara

Causal models defined in terms of structural equations have proved to be quite a powerful way of representing knowledge regarding causality. However, a number of authors have given examples that seem to show that the Halpern-Pearl (HP)…

人工智能 · 计算机科学 2019-02-20 Joseph Y. Halpern

Explainable recommendation systems leverage transparent reasoning to foster user trust and improve decision-making processes. Current approaches typically decouple recommendation generation from explanation creation, violating causal…

人工智能 · 计算机科学 2025-03-12 Guanrong Li , Haolin Yang , Xinyu Liu , Zhen Wu , Xinyu Dai

I develop a novel semantics for probabilities of counterfactuals that generalizes the standard Pearlian semantics: it applies to probabilistic causal models that cannot be extended into realistic structural causal models and are therefore…

人工智能 · 计算机科学 2025-12-16 Sander Beckers

This paper explores the space of (propositional) probabilistic logical languages, ranging from a purely `qualitative' comparative language to a highly `quantitative' language involving arbitrary polynomials over probability terms. While…

‹ 上一页 1 2 3 10 下一页 ›