English
Related papers

Related papers: Causality is Key for Interpretability Claims to Ge…

200 papers

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…

This paper proposes a causal inference relation and causal programming as general frameworks for causal inference with structural causal models. A tuple, $\langle M, I, Q, F \rangle$, is an instance of the relation if a formula, $F$,…

Methodology · Statistics 2018-05-08 Joshua Brulé

Generating explanations for reinforcement learning (RL) is challenging as actions may produce long-term effects on the future. In this paper, we develop a novel framework for explainable RL by learning a causal world model without prior…

Machine Learning · Computer Science 2024-01-19 Zhongwei Yu , Jingqing Ruan , Dengpeng Xing

Of late, in order to have better acceptability among various domain, researchers have argued that machine intelligence algorithms must be able to provide explanations that humans can understand causally. This aspect, also known as…

Machine Learning · Computer Science 2022-08-24 Satyam Kumar , Vadlamani Ravi

Faithful evaluation of language model capabilities is crucial for deriving actionable insights that can inform model development. However, rigorous causal evaluations in this domain face significant methodological challenges, including…

Machine Learning · Computer Science 2025-06-13 Jikai Jin , Vasilis Syrgkanis , Sham Kakade , Hanlin Zhang

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…

Computation and Language · Computer Science 2024-10-29 Haitao Jiang , Lin Ge , Yuhe Gao , Jianian Wang , Rui Song

Causal reasoning is the main learning and explanation tool used by humans. AI systems should possess causal reasoning capabilities to be deployed in the real world with trust and reliability. Introducing the ideas of causality to machine…

Machine Learning · Computer Science 2021-06-11 Abbavaram Gowtham Reddy

Causal models defined in terms of a collection of equations, as defined by Pearl, are axiomatized here. Axiomatizations are provided for three successively more general classes of causal models: (1) the class of recursive theories (those…

Artificial Intelligence · Computer Science 2014-08-08 Joseph Y. Halpern

What is the difference of a prediction that is made with a causal model and a non-causal model? Suppose we intervene on the predictor variables or change the whole environment. The predictions from a causal model will in general work as…

Methodology · Statistics 2024-04-27 Jonas Peters , Peter Bühlmann , Nicolai Meinshausen

Over the past two decades, considerable strides have been made in advancing neuroscientific techniques, yet challenges remain in attributing causality to observed associations. This review addresses a fundamental issue in observational…

Other Quantitative Biology · Quantitative Biology 2025-11-04 Eric W. Bridgeford , Brian S. Caffo , Maya B. Mathur , Russell A. Poldrack

Reliable causal inference is essential for making decisions in high-stakes areas like medicine, economics, and public policy. However, it remains unclear whether large language models (LLMs) can handle rigorous and trustworthy statistical…

Artificial Intelligence · Computer Science 2026-05-13 Jin Du , Li Chen , Xun Xian , An Luo , Fangqiao Tian , Ganghua Wang , Charles Doss , Xiaotong Shen , Jie Ding

Causal models defined in terms of a collection of equations, as defined by Pearl, are axiomatized here. Axiomatizations are provided for three successively more general classes of causal models: (1) the class of recursive theories (those…

Artificial Intelligence · Computer Science 2007-05-23 Joseph Y. Halpern

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)…

Artificial Intelligence · Computer Science 2019-02-20 Joseph Y. Halpern

Perhaps the most prominent current definition of (actual) causality is due to Halpern and Pearl. It is defined using causal models (also known as structural equations models). We abstract the definition, extracting its key features, so that…

Artificial Intelligence · Computer Science 2025-11-27 Joseph Y. Halpern , Rafael Pass

Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential…

Computation and Language · Computer Science 2024-05-02 Sirui Chen , Bo Peng , Meiqi Chen , Ruiqi Wang , Mengying Xu , Xingyu Zeng , Rui Zhao , Shengjie Zhao , Yu Qiao , Chaochao Lu

As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations. However, strong performance on…

Artificial Intelligence · Computer Science 2026-02-24 Yuzhe Wang , Yaochen Zhu , Jundong Li

The ultimate goal of most scientific studies is to understand the underlying causal mechanism between the involved variables. Structural causal models (SCMs) are widely used to represent such causal mechanisms. Given an SCM, causal queries…

Machine Learning · Statistics 2025-03-21 Beate Sick , Oliver Dürr

Model explainability is essential for the creation of trustworthy Machine Learning models in healthcare. An ideal explanation resembles the decision-making process of a domain expert and is expressed using concepts or terminology that is…

Machine Learning · Computer Science 2021-07-14 Sumedha Singla , Stephen Wallace , Sofia Triantafillou , Kayhan Batmanghelich

Causal Bayesian networks are 'causal' models since they make predictions about interventional distributions. To connect such causal model predictions to real-world outcomes, we must determine which actions in the world correspond to which…

Machine Learning · Statistics 2025-02-04 Frederik Hytting Jørgensen , Luigi Gresele , Sebastian Weichwald

The abilities of humans to understand the world in terms of cause and effect relationships, as well as to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in…

Machine Learning · Computer Science 2024-02-26 Kevin Xia , Elias Bareinboim
‹ Prev 1 4 5 6 7 8 10 Next ›