English
Related papers

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

200 papers

Background: Causal relations in natural language (NL) requirements convey strong, semantic information. Automatically extracting such causal information enables multiple use cases, such as test case generation, but it also requires to…

Software Engineering · Computer Science 2022-01-21 Julian Frattini , Jannik Fischbach , Daniel Mendez , Michael Unterkalmsteiner , Andreas Vogelsang , Krzystof Wnuk

Explainability plays an increasingly important role in machine learning. Furthermore, humans view the world through a causal lens and thus prefer causal explanations over associational ones. Therefore, in this paper, we develop a causal…

Artificial Intelligence · Computer Science 2023-07-04 Xiaoxiao Wang , Fanyu Meng , Xin Liu , Zhaodan Kong , Xin Chen

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making…

Despite the recent successes of large, pretrained neural language models (LLMs), comparatively little is known about the representations of linguistic structure they learn during pretraining, which can lead to unexpected behaviors in…

Computation and Language · Computer Science 2024-12-24 Adam Davies , Jize Jiang , ChengXiang Zhai

Multilingual language models achieve strong aggregate performance yet often behave unpredictably across languages, scripts, and cultures. We argue that mechanistic explanations for such models should satisfy a \emph{causal} standard: claims…

Computation and Language · Computer Science 2026-01-01 Yanan Long

Conditional acceptability refers to how plausible a conditional statement is perceived to be. It plays an important role in communication and reasoning, as it influences how individuals interpret implications, assess arguments, and make…

Computation and Language · Computer Science 2026-03-20 Jasmin Orth , Philipp Mondorf , Barbara Plank

A predictive model makes outcome predictions based on some given features, i.e., it estimates the conditional probability of the outcome given a feature vector. In general, a predictive model cannot estimate the causal effect of a feature…

Machine Learning · Computer Science 2023-04-11 Jiuyong Li , Lin Liu , Ziqi Xu , Ha Xuan Tran , Thuc Duy Le , Jixue Liu

Schema-guided reasoning pipelines ask LLMs to produce explicit intermediate structures -- rubrics, checklists, verification queries -- before committing to a final decision. But do these structures causally determine the output, or merely…

Artificial Intelligence · Computer Science 2026-03-18 Oleg Somov , Mikhail Chaichuk , Mikhail Seleznyov , Alexander Panchenko , Elena Tutubalina

There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level…

Artificial Intelligence · Computer Science 2021-06-09 Yu-Liang Chou , Catarina Moreira , Peter Bruza , Chun Ouyang , Joaquim Jorge

Causal machine learning (CML) has experienced increasing popularity in healthcare. Beyond the inherent capabilities of adding domain knowledge into learning systems, CML provides a complete toolset for investigating how a system would react…

Machine Learning · Computer Science 2022-06-01 Pedro Sanchez , Jeremy P. Voisey , Tian Xia , Hannah I. Watson , Alison Q. ONeil , Sotirios A. Tsaftaris

Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. Despite recent advancements in large vision-language models (LVLMs), their ability to comprehend causality remains…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Meiqi Chen , Bo Peng , Yan Zhang , Chaochao Lu

Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. But what exactly in the training data causes a model to make a certain prediction? We seek to answer this question by…

Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a…

Computers and Society · Computer Science 2026-05-08 Isabelle Lee , Emmy Liu , Cathy Jiao , Brihi Joshi , Dani Yogatama , Fazl Barez , Michael Saxon

The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracted as a higher-level algorithm if there exists a function…

Machine Learning · Computer Science 2025-11-13 Denis Sutter , Julian Minder , Thomas Hofmann , Tiago Pimentel

Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small…

Computation and Language · Computer Science 2023-03-08 Peyman Jalali , Nengfeng Zhou , Yufei Yu

We propose a decision theoretic framework that allows a decision maker to express its causal model of the world. We extend the model of Savage (1972) by allowing the decision maker (DM) to choose policy interventions prior to choosing acts…

Theoretical Economics · Economics 2024-07-23 Pablo Schenone

Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a dataset are, in fact,…

Machine Learning · Computer Science 2023-07-13 Avinash Kori , Pedro Sanchez , Konstantinos Vilouras , Ben Glocker , Sotirios A. Tsaftaris

This thesis develops methods for causal inference and causal representation learning (CRL) in high-dimensional, time-varying data. The first contribution introduces the Causal Dynamic Variational Autoencoder (CDVAE), a model for estimating…

Machine Learning · Statistics 2025-12-05 Mouad EL Bouchattaoui

Some interpersonal verbs can implicitly attribute causality to either their subject or their object and are therefore said to carry an implicit causality (IC) bias. Through this bias, causal links can be inferred from a narrative, aiding…

Computation and Language · Computer Science 2021-06-03 Yova Kementchedjhieva , Mark Anderson , Anders Søgaard

Causal approaches to post-hoc explainability for black-box prediction models (e.g., deep neural networks trained on image pixel data) have become increasingly popular. However, existing approaches have two important shortcomings: (i) the…

Machine Learning · Computer Science 2025-08-12 Numair Sani , Daniel Malinsky , Ilya Shpitser