English
Related papers

Related papers: Does Debiasing Inevitably Degrade the Model Perfor…

200 papers

Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods,…

Computation and Language · Computer Science 2024-05-27 Hillary Dawkins , Isar Nejadgholi , Daniel Gillis , Judi McCuaig

Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always…

Computation and Language · Computer Science 2025-04-02 Lucy Havens , Benjamin Bach , Melissa Terras , Beatrice Alex

Machine Learning models have been deployed across many different aspects of society, often in situations that affect social welfare. Although these models offer streamlined solutions to large problems, they may contain biases and treat…

Machine Learning · Computer Science 2021-06-22 Tal Feldman , Ashley Peake

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions of bias, means of quantification, and oftentimes vague…

Computation and Language · Computer Science 2023-02-14 Xudong Han , Timothy Baldwin , Trevor Cohn

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…

Computation and Language · Computer Science 2024-11-20 Navya Yarrabelly , Vinay Damodaran , Feng-Guang Su

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

Computation and Language · Computer Science 2019-06-03 Kaiji Lu , Piotr Mardziel , Fangjing Wu , Preetam Amancharla , Anupam Datta

Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender-related biases, and how these influence the meta-embeddings has not been studied…

Computation and Language · Computer Science 2022-10-07 Masahiro Kaneko , Danushka Bollegala , Naoaki Okazaki

Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…

Computation and Language · Computer Science 2022-10-28 Jacqueline He , Mengzhou Xia , Christiane Fellbaum , Danqi Chen

Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary research suggests that…

Computation and Language · Computer Science 2022-03-22 Eve Fleisig , Christiane Fellbaum

With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted…

Computation and Language · Computer Science 2021-06-17 Gauri Gupta , Krithika Ramesh , Sanjay Singh

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are…

Computation and Language · Computer Science 2020-05-04 Prasetya Ajie Utama , Nafise Sadat Moosavi , Iryna Gurevych

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…

Computation and Language · Computer Science 2024-08-28 Atmika Gorti , Manas Gaur , Aman Chadha

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Computation and Language · Computer Science 2024-10-21 Thomas Uriot

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When…

Information Retrieval · Computer Science 2025-11-04 Amirabbas Afzali , Amirreza Velae , Iman Ahmadi , Mohammad Aliannejadi

This paper investigates the transferability of debiasing techniques across different languages within multilingual models. We examine the applicability of these techniques in English, French, German, and Dutch. Using multilingual BERT…

Computation and Language · Computer Science 2023-10-17 Manon Reusens , Philipp Borchert , Margot Mieskes , Jochen De Weerdt , Bart Baesens

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…

Computation and Language · Computer Science 2023-10-24 Bodhisattwa Prasad Majumder , Zexue He , Julian McAuley

The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both results on debiasing methods in the literature and reports of…

Computation and Language · Computer Science 2024-05-14 David F. Jenny , Yann Billeter , Mrinmaya Sachan , Bernhard Schölkopf , Zhijing Jin

This paper proposes two intuitive metrics, skew and stereotype, that quantify and analyse the gender bias present in contextual language models when tackling the WinoBias pronoun resolution task. We find evidence that gender stereotype…

Computation and Language · Computer Science 2021-02-17 Daniel de Vassimon Manela , David Errington , Thomas Fisher , Boris van Breugel , Pasquale Minervini

Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1)…

Computation and Language · Computer Science 2020-01-06 Anne Lauscher , Goran Glavaš , Simone Paolo Ponzetto , Ivan Vulić

Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing. However, this kind of methods may suffer from the branching bias issue, which…

Computation and Language · Computer Science 2020-12-17 Huayang Li , Lemao Liu , Guoping Huang , Shuming Shi