Related papers: Gender Encoding Patterns in Pretrained Language Mo…
During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured…
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…
Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of…
Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for…
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…
As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in…
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, when trained…
Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and…
Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an…
Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…
Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representation of gender…
With the growing deployment of large language models (LLMs) across various applications, assessing the influence of gender biases embedded in LLMs becomes crucial. The topic of gender bias within the realm of natural language processing…
Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on…
Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the…
Pre-trained models have revolutionized natural language understanding. However, researchers have found they can encode artifacts undesired in many applications, such as professions correlating with one gender more than another. We explore…
(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation…
Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…
In recent years, various methods have been proposed to evaluate gender bias in large language models (LLMs). A key challenge lies in the transferability of bias measurement methods initially developed for the English language when applied…