English
Related papers

Related papers: Marked Attribute Bias in Natural Language Inferenc…

200 papers

Social biases are encoded in word embeddings. This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications. Here, we investigate the extent to which…

Computation and Language · Computer Science 2020-04-28 Kenneth Joseph , Jonathan H. Morgan

Language Representation Models (LRMs) trained with real-world data may capture and exacerbate undesired bias and cause unfair treatment of people in various demographic groups. Several techniques have been investigated for applying…

Computation and Language · Computer Science 2023-11-14 Chloe Qinyu Zhu , Rickard Stureborg , Brandon Fain

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this…

Machine Learning · Computer Science 2022-03-30 Thomas Demeester , Johannes Deleu , Fréderic Godin , Chris Develder

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Machine Learning · Computer Science 2023-06-06 Lukas Hauzenberger , Shahed Masoudian , Deepak Kumar , Markus Schedl , Navid Rekabsaz

Pre-trained word embeddings are the primary method for transfer learning in several Natural Language Processing (NLP) tasks. Recent works have focused on using unsupervised techniques such as language modeling to obtain these embeddings. In…

Computation and Language · Computer Science 2019-07-01 Mihir Kale , Aditya Siddhant , Sreyashi Nag , Radhika Parik , Matthias Grabmair , Anthony Tomasic

We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose difficulties to NLP systems; and develop tests…

Computation and Language · Computer Science 2016-06-28 Yadollah Yaghoobzadeh , Hinrich Schütze

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Computation and Language · Computer Science 2026-02-05 Yujie Lin , Kunquan Li , Yixuan Liao , Xiaoxin Chen , Jinsong Su

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Computation and Language · Computer Science 2021-09-10 Timo Schick , Sahana Udupa , Hinrich Schütze

Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently,…

Computation and Language · Computer Science 2023-02-24 Jad Doughman , Wael Khreich

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

Computers and Society · Computer Science 2026-04-14 Anay Agarwalla , Simeon Sayer

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

Computation and Language · Computer Science 2021-12-28 Mikel Artetxe , Gorka Labaka , Iñigo Lopez-Gazpio , Eneko Agirre

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

This study examines the use of natural language processing (NLP) models to evaluate whether language patterns used by item writers in a medical licensure exam might contain evidence of biased or stereotypical language. This type of bias in…

Computation and Language · Computer Science 2021-11-23 Swati Padhee , Kimberly Swygert , Ian Micir

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those…

Computation and Language · Computer Science 2023-06-28 Sophie Jentzsch , Cigdem Turan

We investigate the potential for nationality biases in natural language processing (NLP) models using human evaluation methods. Biased NLP models can perpetuate stereotypes and lead to algorithmic discrimination, posing a significant…

Computation and Language · Computer Science 2023-08-09 Pranav Narayanan Venkit , Sanjana Gautam , Ruchi Panchanadikar , Ting-Hao `Kenneth' Huang , Shomir Wilson

Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social…

Computation and Language · Computer Science 2020-05-05 Ben Hutchinson , Vinodkumar Prabhakaran , Emily Denton , Kellie Webster , Yu Zhong , Stephen Denuyl

Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce translation quality, particularly when the target language…

Computation and Language · Computer Science 2020-07-10 Danielle Saunders , Bill Byrne

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate…

Computation and Language · Computer Science 2019-11-26 He He , Sheng Zha , Haohan Wang

Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few…

Computation and Language · Computer Science 2025-07-02 David Ifeoluwa Adelani