Related papers: Measuring and Reducing Gendered Correlations in Pr…

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes…

Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this…

Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this…

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method…

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks…

Accurately measuring gender stereotypical bias in language models is a complex task with many hidden aspects. Current benchmarks have underestimated this multifaceted challenge and failed to capture the full extent of the problem. This…

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of…

Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to…

Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code. Aside from aiding programming-related tasks, anecdotal evidence suggests that including code in pretraining…

Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled…

Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and society at large. As a…

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

Physical measurements constitute a large portion of numbers in academic papers, engineering reports, and web tables. Current benchmarks fall short of properly evaluating numeracy of pretrained language models on measurements, hindering…

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…

Domain generalization aims to build generalized models that perform well on unseen domains when only source domains are available for model optimization. Recent studies have shown that large-scale pre-trained models can enhance domain…

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model…

Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built…

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…