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