English
Related papers

Related papers: Towards Debiasing Sentence Representations

200 papers

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Computation and Language · Computer Science 2021-09-10 Michael Mendelson , Yonatan Belinkov

Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and…

Computation and Language · Computer Science 2025-02-28 Ruizhe Chen , Yichen Li , Jianfei Yang , Joey Tianyi Zhou , Jian Wu , Zuozhu Liu

Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…

Machine Learning · Computer Science 2023-05-16 Ching-Yao Chuang , Varun Jampani , Yuanzhen Li , Antonio Torralba , Stefanie Jegelka

Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling. We conduct the…

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Computation and Language · Computer Science 2016-10-07 Kim Anh Nguyen , Sabine Schulte im Walde , Ngoc Thang Vu

The enormous amount of data being generated on the web and social media has increased the demand for detecting online hate speech. Detecting hate speech will reduce their negative impact and influence on others. A lot of effort in the…

Computation and Language · Computer Science 2021-11-03 Hind Saleh , Areej Alhothali , Kawthar Moria

The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory…

Computation and Language · Computer Science 2026-03-03 Maureen Herbert , Katie Sun , Angelica Lim , Yasaman Etesam

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

Computation and Language · Computer Science 2024-08-20 Rameez Qureshi , Naïm Es-Sebbani , Luis Galárraga , Yvette Graham , Miguel Couceiro , Zied Bouraoui

Bias in Word Embeddings has been a subject of recent interest, along with efforts for its reduction. Current approaches show promising progress towards debiasing single bias dimensions such as gender or race. In this paper, we present a…

Computation and Language · Computer Science 2020-03-26 Radomir Popović , Florian Lemmerich , Markus Strohmaier

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word…

Computers and Society · Computer Science 2021-05-20 Wei Guo , Aylin Caliskan

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Haoyu Zhang , Yangyang Guo , Mohan Kankanhalli

Over the last years, word and sentence embeddings have established as text preprocessing for all kinds of NLP tasks and improved the performances significantly. Unfortunately, it has also been shown that these embeddings inherit various…

Computation and Language · Computer Science 2024-09-13 Sarah Schröder , Alexander Schulz , Philip Kenneweg , Robert Feldhans , Fabian Hinder , Barbara Hammer

Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using…

Computation and Language · Computer Science 2024-09-24 Deonna M. Owens , Ryan A. Rossi , Sungchul Kim , Tong Yu , Franck Dernoncourt , Xiang Chen , Ruiyi Zhang , Jiuxiang Gu , Hanieh Deilamsalehy , Nedim Lipka

Text representation models are prone to exhibit a range of societal biases, reflecting the non-controlled and biased nature of the underlying pretraining data, which consequently leads to severe ethical issues and even bias amplification.…

Computation and Language · Computer Science 2021-06-08 Soumya Barikeri , Anne Lauscher , Ivan Vulić , Goran Glavaš

Due to the presence of political echo chambers, it becomes imperative to detect and remove subjective bias and emotionally charged language from both the text and images of political articles. However, prior work has focused on solely the…

Computers and Society · Computer Science 2025-06-24 Cedric Bernard , Xavier Pleimling , Amun Kharel , Chase Vickery

Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…

Artificial Intelligence · Computer Science 2026-02-03 Deep Gandhi , Katyani Singh , Nidhi Hegde

Although much work in NLP has focused on measuring and mitigating stereotypical bias in semantic spaces, research addressing bias in computational argumentation is still in its infancy. In this paper, we address this research gap and…

Computation and Language · Computer Science 2022-04-11 Carolin Holtermann , Anne Lauscher , Simone Paolo Ponzetto

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes…

Computation and Language · Computer Science 2021-06-15 Taeuk Kim , Kang Min Yoo , Sang-goo Lee

One popular method for quantitatively evaluating the utility of sentence embeddings involves using them in downstream language processing tasks that require sentence representations as input. One simple such task is classification, where…

Computation and Language · Computer Science 2019-05-28 Peter Potash

Previous work has examined how debiasing language models affect downstream tasks, specifically, how debiasing techniques influence task performance and whether debiased models also make impartial predictions in downstream tasks or not.…

Computation and Language · Computer Science 2022-06-03 Sullam Jeoung , Jana Diesner