Related papers: NLP needs Diversity outside of 'Diversity'

Current natural language processing (NLP) research tends to focus on only one or, less frequently, two dimensions - e.g., performance, privacy, fairness, or efficiency - at a time, which may lead to suboptimal conclusions and often…

In a recent study by Ginther et al., the probability of receiving a U.S. National Institutes of Health (NIH) RO1 award was related to the applicant's race/ethnicity. The results indicate black/African-American applicants were 10% less…

Promoting diversity in the music sector is widely discussed on the media. While the major problem may lie deep in our society, music information retrieval contributes to promoting diversity or may create unequal opportunities for artists.…

Studies on supervised machine learning (ML) recommend involving workers from various backgrounds in training dataset labeling to reduce algorithmic bias. Moreover, sophisticated tasks for categorizing objects in images are necessary to…

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in…

Conducting disparity assessments at regular time intervals is critical for surfacing potential biases in decision-making and improving outcomes across demographic groups. Because disparity assessments fundamentally depend on the…

Large Language Models (LLMs) are increasingly used for accessibility guidance, yet many disability groups remain underserved by their advice. To address this gap, we present taxonomy aligned benchmark1 of human validated, general purpose…

As large language models (LLMs) like GPT-4 and Llama 3 become integral to educational contexts, concerns are mounting over the cultural biases, power imbalances, and ethical limitations embedded within these technologies. Though generative…

Access to content and services online is increasingly important for everyone, including people with disabilities. National commitments, including the Americans with Disabilities Act, and international resolutions, including the United…

We consider online resource allocation under a typical non-profit setting, where limited or even scarce resources are administered by a not-for-profit organization like a government. We focus on the internal-equity by assuming that arriving…

Although much literature has established the presence of demographic bias in natural language processing (NLP) models, most work relies on curated bias metrics that may not be reflective of real-world applications. At the same time,…

Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…

Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing.…

In sequential decision-making problems involving sensitive attributes like race and gender, reinforcement learning (RL) agents must carefully consider long-term fairness while maximizing returns. Recent works have proposed many different…

Bias research in NLP seeks to analyse models for social biases, thus helping NLP practitioners uncover, measure, and mitigate social harms. We analyse the body of work that uses prompts and templates to assess bias in language models. We…

English has long been assumed the $\textit{lingua franca}$ of scientific research, and this notion is reflected in the natural language processing (NLP) research involving scientific document representation. In this position piece, we…

Clinical NLP has an immense potential in contributing to how clinical practice will be revolutionized by the advent of large scale processing of clinical records. However, this potential has remained largely untapped due to slow progress…

Recent literature on computational notions of fairness has been broadly divided into two distinct camps, supporting interventions that address either individual-based or group-based fairness. Rather than privilege a single definition, we…

Algorithmic tools are increasingly used in hiring to improve fairness and diversity, often by enforcing constraints such as gender-balanced candidate shortlists. However, we show theoretically and empirically that enforcing equal…

The ability of LLMs to represent diverse perspectives is critical as they increasingly impact society. However, recent studies reveal that alignment algorithms such as RLHF and DPO significantly reduce the diversity of LLM outputs. Not only…