English
Related papers

Related papers: D-Separation for Causal Self-Explanation

200 papers

LLM-as-a-judge models have been used for evaluating both human and AI generated content, specifically by providing scores and rationales. Rationales, in addition to increasing transparency, help models learn to calibrate its judgments.…

Discovering causal relationships from time series data is significant in fields such as finance, climate science, and neuroscience. However, contemporary techniques rely on the simplifying assumption that data originates from the same…

Machine Learning · Computer Science 2024-06-25 Sumanth Varambally , Yi-An Ma , Rose Yu

Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuations, complicating causal inference under non-stationarity and autocorrelation.…

Machine Learning · Computer Science 2026-04-29 Muhammad Hasan Ferdous , Md Osman Gani

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Computation and Language · Computer Science 2021-12-07 George Chrysostomou , Nikolaos Aletras

Discovering the causal structure among a set of variables is a fundamental problem in many areas of science. In this paper, we propose Kernel Conditional Deviance for Causal Inference (KCDC) a fully nonparametric causal discovery method…

Machine Learning · Computer Science 2018-04-13 Jovana Mitrovic , Dino Sejdinovic , Yee Whye Teh

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and…

Computation and Language · Computer Science 2024-02-12 Lu Chen , Wei Huang , Ruqing Zhang , Wei Chen , Jiafeng Guo , Xueqi Cheng

The two most commonly used criteria for assessing causal model discovery with artificial data are edit-distance and Kullback-Leibler divergence, measured from the true model to the learned model. Both of these metrics maximally reward the…

Machine Learning · Computer Science 2021-11-12 Rodney T. O'Donnell , Kevin B. Korb , Lloyd Allison

Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic…

Computation and Language · Computer Science 2025-05-01 Thanushon Sivakaran , En-Hui Yang

We address the problem of determining the causal direction between two univariate, continuous-valued variables, X and Y, under the assumption of no hidden confounders. In general, it is not possible to make definitive statements about…

Machine Learning · Statistics 2025-09-03 Katerina Hlavackova-Schindler , Suzana Marsela

CDD, or Contamination Detection via output Distribution, identifies data contamination by measuring the peakedness of a model's sampled outputs. We study the conditions under which this approach succeeds and fails on small language models…

Artificial Intelligence · Computer Science 2026-03-12 Omer Sela

With recent developments in Social Computing, Natural Language Processing and Clinical Psychology, the social NLP research community addresses the challenge of automation in mental illness on social media. A recent extension to the problem…

Computation and Language · Computer Science 2022-11-10 Chandni Saxena , Muskan Garg , Gunjan Ansari

Large proprietary language models exhibit strong causal reasoning abilities that smaller open-source models struggle to replicate. We introduce a novel framework for distilling causal explanations that transfers causal reasoning skills from…

Computation and Language · Computer Science 2025-05-27 Aggrey Muhebwa , Khalid K. Osman

We propose a novel approach for learning causal response representations. Our method aims to extract directions in which a multidimensional outcome is most directly caused by a treatment variable. By bridging conditional independence…

Machine Learning · Statistics 2025-03-07 Homer Durand , Gherardo Varando , Gustau Camps-Valls

The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other. While this idea has led to fruitful developments in the…

Computation and Language · Computer Science 2021-10-20 Zhijing Jin , Julius von Kügelgen , Jingwei Ni , Tejas Vaidhya , Ayush Kaushal , Mrinmaya Sachan , Bernhard Schölkopf

Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges. The former…

Artificial Intelligence · Computer Science 2024-06-12 Kai-Hendrik Cohrs , Gherardo Varando , Emiliano Diaz , Vasileios Sitokonstantinou , Gustau Camps-Valls

Adaptive machine learning (ML) aims to allow ML models to adapt to ever-changing environments with potential concept drift after model deployment. Traditionally, adaptive ML requires a new dataset to be manually labeled to tailor deployed…

Machine Learning · Computer Science 2024-04-10 Yutian Ren , Aaron Haohua Yen , G. P. Li

Mechanistic interpretability papers increasingly use causal vocabulary: circuits, mediators, causal abstraction, monosemanticity. Such claims require explicit identification assumptions. A purposive audit of 10 papers across four…

Machine Learning · Computer Science 2026-05-11 Zezheng Lin , Fengming Liu

Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend only on the joint distribution of predictor, protected…

The rules of d-separation provide a framework for deriving conditional independence facts from model structure. However, this theory only applies to simple directed graphical models. We introduce relational d-separation, a theory for…

Artificial Intelligence · Computer Science 2013-04-16 Marc Maier , David Jensen

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI…

Machine Learning · Computer Science 2019-01-30 Chenguang Lu