Related papers: Debiasing Stance Detection Models with Counterfact…

VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language. Recent debiasing methods proposed to exclude the language prior during inference.…

Vision-language (VL) understanding tasks evaluate models' comprehension of complex visual scenes through multiple-choice questions. However, we have identified two dataset biases that models can exploit as shortcuts to resolve various VL…

The large majority of the research performed on stance detection has been focused on developing more or less sophisticated text classification systems, even when many benchmarks are based on social network data such as Twitter. This paper…

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

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…

Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets. Previous work on stance detection largely focused on pure texts. In this paper, we study multi-modal…

A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, these methods often perform poorly in the face of biased data,…

Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar…

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly,…

Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are…

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

Fair machine learning aims to mitigate the biases of model predictions against certain subpopulations regarding sensitive attributes such as race and gender. Among the many existing fairness notions, counterfactual fairness measures the…

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applications, these biases…

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice.…

Stance detection has emerged as a popular task in natural language processing research, enabled largely by the abundance of target-specific social media data. While there has been considerable research on the development of stance detection…

This tutorial aims to cover the state-of-the-art on stance detection and address open research avenues for interested researchers and practitioners. Stance detection is a recent research topic where the stance towards a given target or…

Prior studies of zero-shot stance detection identify the attitude of texts towards unseen topics occurring in the same document corpus. Such task formulation has three limitations: (i) Single domain/dataset. A system is optimized on a…