bias

Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models

Emotions play important epistemological and cognitive roles in our lives, revealing our values and guiding our actions. Previous work has shown that LLMs display biases in emotion attribution along gender lines. However, unlike gender, which says …

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

Machine learning models are now able to convert user-written text descriptions into naturalistic images. These models are available to anyone online and are being used to generate millions of images a day. We investigate these models and find that …

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms …

SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems

The social impact of natural language processing and its applications has received increasing attention. In this position paper, we focus on the problem of safety for end-to-end conversational AI. We survey the problem landscape therein, introducing …

Five sources of bias in natural language processing

Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much of the recent work has focused on describing bias and providing an overview of bias in a larger context. Here, we …

Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview

An increasing number of natural language processing papers address the effect of bias on predictions, introducing mitigation techniques at different parts of the standard NLP pipeline (data and models). However, these works have been conducted …

“You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases

The main goal of machine translation has been to convey the correct content. Stylistic considerations have been at best secondary. We show that as a consequence, the output of three commercial machine translation systems (Bing, DeepL, Google) make …

Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing

Several linguistic studies have shown the prevalence of various lexical and grammatical patterns in texts authored by a person of a particular gender, but models for part-of-speech tagging and dependency parsing have still not adapted to account for …