Related papers: End-to-End Bias Mitigation by Modelling Biases in …

Recent advances in large language models (LLMs) have substantially improved natural language processing (NLP) applications. However, these models often inherit and amplify biases present in their training data. Although several datasets…

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…

Recent years have seen a growing number of publications that analyse Natural Language Inference (NLI) datasets for superficial cues, whether they undermine the complexity of the tasks underlying those datasets and how they impact those…

Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Current natural language understanding (NLU) models have been continuously scaling up, both in terms of model size and input context, introducing more hidden and input neurons. While this generally improves performance on average, the extra…

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased…

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition. However, the causality and latency constraints of production systems put end-to-end…

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly…

Large language models have demonstrated strong capabilities to learn in-context, where exemplar input-output pairings are appended to the prompt for demonstration. However, existing work has demonstrated the ability of models to learn…

Phenomenon-specific "adversarial" datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training NLI and other…

Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Large Language Models (LLMs) have fundamentally transformed the field of natural language processing; however, their vulnerability to biases presents a notable obstacle that threatens both fairness and trust. This review offers an extensive…

A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic…

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of…

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…

Models that adapt their predictions based on some given contexts, also known as in-context learning, have become ubiquitous in recent years. We propose to study the behavior of such models when data is contaminated by noise. Towards this…

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to…