Related papers: Conceptualizing Treatment Leakage in Text-based Ca…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Estimating treatment effects plays a crucial role in causal inference, having many real-world applications like policy analysis and decision making. Nevertheless, estimating treatment effects in the longitudinal setting in the presence of…

Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive…

We propose a machine-learning tool that yields causal inference on text in randomized trials. Based on a simple econometric framework in which text may capture outcomes of interest, our procedure addresses three questions: First, is the…

In causal mediation studies that decompose an average treatment effect into a natural indirect effect (NIE) and a natural direct effect (NDE), examples of post-treatment confounding are abundant. Past research has generally considered it…

One of the major challenges in estimating conditional potential outcomes and conditional average treatment effects (CATE) is the presence of hidden confounders. Since testing for hidden confounders cannot be accomplished only with…

Unobserved confounding presents a major threat to causal inference from observational studies. Recently, several authors suggest that this problem may be overcome in a shared confounding setting where multiple treatments are independent…

The ubiquity of complex machine learning has raised the importance of model-agnostic explanation algorithms. These methods create artificial instances by slightly perturbing real instances, capturing shifts in model decisions. However, such…

Understanding the effects of interventions is central to scientific progress, with randomized controlled trials (RCTs) regarded as the gold standard for causal inference in many applied fields. However, RCTs are costly, time-consuming, and…

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing…

Recent advances in natural language processing have enabled the increasing use of text data in causal inference, particularly for adjusting confounding factors in treatment effect estimation. Although high-dimensional text can encode rich…

Inferring causal effects of treatments is a central goal in many disciplines. The potential outcomes framework is a main statistical approach to causal inference, in which a causal effect is defined as a comparison of the potential outcomes…

Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a…

When constructing a model to estimate the causal effect of a treatment, it is necessary to control for other factors which may have confounding effects. Because the ignorability assumption is not testable, however, it is usually unclear…

Treatment policy estimands are frequently favored by regulators, as they assess the effect of treatment assignment regardless of post-randomization events. Despite best efforts, missing data due to study discontinuation cannot be fully…

Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…

A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has…

The goal of causal inference is to understand the outcome of alternative courses of action. However, all causal inference requires assumptions. Such assumptions can be more influential than in typical tasks for probabilistic modeling, and…