Related papers: CausalAPM: Generalizable Literal Disentanglement f…
Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading…
When applying machine learning to problems in NLP, there are many choices to make about how to represent input texts. These choices can have a big effect on performance, but they are often uninteresting to researchers or practitioners who…
Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all contradiction…
In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that…
Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transformations. Among the…
Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing. However, undesired patterns in the collected data can make such tests incorrect. For example, if the…
Unobserved confounding is common in many applications, making causal inference from observational data challenging. As a remedy, causal sensitivity analysis is an important tool to draw causal conclusions under unobserved confounding with…
Causal disentanglement seeks a representation of data involving latent variables that relate to one another via a causal model. A representation is identifiable if both the latent model and the transformation from latent to observed…
Multimodal Large Language Models (MLLMs) have emerged as a central focus in both industry and academia, but often suffer from biases introduced by visual and language priors, which can lead to multimodal hallucination. These biases arise…
The remarkable progress in Natural Language Processing (NLP) brought about by deep learning, particularly with the recent advent of large pre-trained neural language models, is brought into scrutiny as several studies began to discuss and…
Despite the overwhelming performance improvements offered by recent natural language processing (NLP) models, the decisions made by these models are largely a black box. Towards closing this gap, the field of causal NLP combines causal…
Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they are trained on, while not generalising to different task…
Many questions in Data Science are fundamentally causal in that our objective is to learn the effect of some exposure, randomized or not, on an outcome interest. Even studies that are seemingly non-causal, such as those with the goal of…
Traditional recommendation models trained on observational interaction data have generated large impacts in a wide range of applications, it faces bias problems that cover users' true intent and thus deteriorate the recommendation…
With the advent of larger and more complex deep learning models, such as in Natural Language Processing (NLP), model qualities like explainability and interpretability, albeit highly desirable, are becoming harder challenges to tackle and…
When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of $X$ conditional on $Y = 1$, where X stands for the feature and Y the label. Most…
Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…
Public datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train and test datasets can lead to…
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images.…
Cognitive biases, systematic deviations from rationality in judgment, pose significant challenges in generating objective content. This paper introduces a novel approach for real-time cognitive bias detection in user-generated text using…