English
Related papers

Related papers: Applying Intrinsic Debiasing on Downstream Tasks: …

200 papers

Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested…

Computation and Language · Computer Science 2026-03-05 Janiça Hackenbuchner , Arda Tezcan , Joke Daems

Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance…

Computation and Language · Computer Science 2021-07-27 Jonas-Dario Troles , Ute Schmid

Language models are the new state-of-the-art natural language processing (NLP) models and they are being increasingly used in many NLP tasks. Even though there is evidence that language models are biased, the impact of that bias on the…

Computation and Language · Computer Science 2024-04-29 Fatma Elsafoury , Stamos Katsigiannis

Neural machine translation (NMT) models often suffer from gender biases that harm users and society at large. In this work, we explore how bridging the gap between languages for which parallel data is not available affects gender bias in…

Computation and Language · Computer Science 2023-05-29 Lena Cabrera , Jan Niehues

Gender bias in artificial intelligence (AI) has emerged as a pressing concern with profound implications for individuals' lives. This paper presents a comprehensive survey that explores gender bias in Transformer models from a linguistic…

Computation and Language · Computer Science 2023-06-21 Praneeth Nemani , Yericherla Deepak Joel , Palla Vijay , Farhana Ferdousi Liza

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

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Machine Learning · Computer Science 2023-08-25 Yi Zhang , Jitao Sang , Junyang Wang , Dongmei Jiang , Yaowei Wang

Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately, multiple sources have shown that the bias, inherent in the…

Computation and Language · Computer Science 2024-03-28 Philip Kenneweg , Sarah Schröder , Alexander Schulz , Barbara Hammer

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…

Computation and Language · Computer Science 2019-08-19 Apik Ashod Zorian , Chandra Shekar Bikkanur

Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, various image translation and debiasing methods have attempted to…

Computer Vision and Pattern Recognition · Computer Science 2023-01-04 Myeongkyun Kang , Dongkyu Won , Miguel Luna , Philip Chikontwe , Kyung Soo Hong , June Hong Ahn , Sang Hyun Park

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Angelina Wang , Olga Russakovsky

We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in…

Computation and Language · Computer Science 2023-10-03 Bar Iluz , Tomasz Limisiewicz , Gabriel Stanovsky , David Mareček

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Computation and Language · Computer Science 2026-03-09 Schrasing Tong , Eliott Zemour , Jessica Lu , Rawisara Lohanimit , Lalana Kagal

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with…

Computation and Language · Computer Science 2022-05-26 Lu Cheng , Suyu Ge , Huan Liu

Contextual language models (CLMs) have pushed the NLP benchmarks to a new height. It has become a new norm to utilize CLM provided word embeddings in downstream tasks such as text classification. However, unless addressed, CLMs are prone to…

Computation and Language · Computer Science 2020-09-11 Rishabh Bhardwaj , Navonil Majumder , Soujanya Poria

Despite the recent success of artificial neural networks on a variety of tasks, we have little knowledge or control over the exact solutions these models implement. Instilling inductive biases -- preferences for some solutions over others…

Machine Learning · Computer Science 2024-02-02 Enyan Zhang , Michael A. Lepori , Ellie Pavlick

Word embeddings are extensively used in various NLP problems as a state-of-the-art semantic feature vector representation. Despite their success on various tasks and domains, they might exhibit an undesired bias for stereotypical categories…

Computation and Language · Computer Science 2022-12-16 Gizem Sogancioglu , Heysem Kaya

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model editing methods, which focus on modifying LLMs in a post-hoc…

Computation and Language · Computer Science 2024-02-22 Jianhao Yan , Futing Wang , Yafu Li , Yue Zhang

Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or…

Computation and Language · Computer Science 2021-09-23 Shivashankar Subramanian , Xudong Han , Timothy Baldwin , Trevor Cohn , Lea Frermann

With the rapid development of large language models (LLMs), they have significantly improved efficiency across a wide range of domains. However, recent studies have revealed that LLMs often exhibit gender bias, leading to serious social…

Computation and Language · Computer Science 2025-06-17 Xiaoqing Cheng , Hongying Zan , Lulu Kong , Jinwang Song , Min Peng
‹ Prev 1 4 5 6 7 8 10 Next ›