Related papers: Towards Debiasing NLU Models from Unknown Biases
As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…
Datasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of bias attributes.…
As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…
Supervised machine learning models and their evaluation strongly depends on the quality of the underlying dataset. When we search for a relevant piece of information it may appear anywhere in a given passage. However, we observe a bias in…
An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and debias PLMs are skewed towards the US racial biases and…
Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…
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…
Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically analyze medical images beforehand, which brings more…
Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…
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…
Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with…
The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…
This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…
Large language models (LLMs) have achieved promising results in tabular data generation. However, inherent historical biases in tabular datasets often cause LLMs to exacerbate fairness issues, particularly when multiple advantaged and…
Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…
Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets…
Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…
The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…
An increasing number of works in natural language processing have addressed the effect of bias on the predicted outcomes, introducing mitigation techniques that act on different parts of the standard NLP pipeline (data and models). However,…
Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…