English
Related papers

Related papers: Gender Encoding Patterns in Pretrained Language Mo…

200 papers

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…

Computation and Language · Computer Science 2026-05-14 Nour Bouchouchi , Thibault Laugel , Xavier Renard , Christophe Marsala , Marie-Jeanne Lesot , Marcin Detyniecki

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…

Computation and Language · Computer Science 2021-05-06 Christine Basta , Marta R. Costa-jussà

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…

Computation and Language · Computer Science 2025-06-18 Erik Derner , Sara Sansalvador de la Fuente , Yoan Gutiérrez , Paloma Moreda , Nuria Oliver

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…

Computation and Language · Computer Science 2023-07-25 Somayeh Ghanbarzadeh , Yan Huang , Hamid Palangi , Radames Cruz Moreno , Hamed Khanpour

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…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

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…

Computation and Language · Computer Science 2019-06-24 Tony Sun , Andrew Gaut , Shirlyn Tang , Yuxin Huang , Mai ElSherief , Jieyu Zhao , Diba Mirza , Elizabeth Belding , Kai-Wei Chang , William Yang Wang

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…

Computation and Language · Computer Science 2020-12-25 Marta R. Costa-jussà , Carlos Escolano , Christine Basta , Javier Ferrando , Roser Batlle , Ksenia Kharitonova

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…

Computation and Language · Computer Science 2025-05-21 Franziska Sofia Hafner , Ana Valdivia , Luc Rocher

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…

Computation and Language · Computer Science 2024-06-18 Yi Yang , Hanyu Duan , Ahmed Abbasi , John P. Lalor , Kar Yan Tam

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,…

Computation and Language · Computer Science 2020-05-05 Jieyu Zhao , Subhabrata Mukherjee , Saghar Hosseini , Kai-Wei Chang , Ahmed Hassan Awadallah

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…

Computation and Language · Computer Science 2024-02-20 Xiangjue Dong , Yibo Wang , Philip S. Yu , James Caverlee

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…

Computation and Language · Computer Science 2022-07-22 Oskar van der Wal , Jaap Jumelet , Katrin Schulz , Willem Zuidema

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…

Computation and Language · Computer Science 2022-08-15 Hila Gonen , Shauli Ravfogel , Yoav Goldberg

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…

Computation and Language · Computer Science 2024-03-04 Jinman Zhao , Yitian Ding , Chen Jia , Yining Wang , Zifan Qian

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…

Computation and Language · Computer Science 2024-06-04 Bar Iluz , Yanai Elazar , Asaf Yehudai , Gabriel Stanovsky

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…

Computation and Language · Computer Science 2025-06-04 Dennis Fucci , Marco Gaido , Matteo Negri , Luisa Bentivogli , Andre Martins , Giuseppe Attanasio

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…

Computation and Language · Computer Science 2021-03-04 Kellie Webster , Xuezhi Wang , Ian Tenney , Alex Beutel , Emily Pitler , Ellie Pavlick , Jilin Chen , Ed Chi , Slav Petrov

(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…

Machine Learning · Computer Science 2019-08-09 Flavien Prost , Nithum Thain , Tolga Bolukbasi

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.…

Computation and Language · Computer Science 2019-06-04 Masahiro Kaneko , Danushka Bollegala

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…

Computation and Language · Computer Science 2025-07-23 Kristin Gnadt , David Thulke , Simone Kopeinik , Ralf Schlüter
‹ Prev 1 2 3 10 Next ›