相关论文: FairHome: A Fair Housing and Fair Lending Dataset

As a basic human need, housing plays a key role in enhancing health, well-being, and educational outcome in society, and the housing market is a major factor for promoting quality of life and ensuring social equity. To improve the housing…

Intersectional fairness is a critical requirement for Machine Learning (ML) software, demanding fairness across subgroups defined by multiple protected attributes. This paper introduces FairHOME, a novel ensemble approach using higher order…

Classification, a heavily-studied data-driven machine learning task, drives an increasing number of prediction systems involving critical human decisions such as loan approval and criminal risk assessment. However, classifiers often…

Large Language Models (LLMs) are increasingly used in high-stakes fields where their decisions impact rights and equity. However, LLMs' judicial fairness and implications for social justice remain underexplored. When LLMs act as judges, the…

Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations,…

Large Language Models (LLMs) are increasingly leveraged for translation tasks but often fall short when translating inclusive language -- such as texts containing the singular 'they' pronoun or otherwise reflecting fair linguistic…

There has been increasing awareness of ethical issues in machine learning, and fairness has become an important research topic. Most fairness efforts in computer vision have been focused on human sensing applications and preventing…

Machine learning (ML) is increasingly being used in high-stakes applications impacting society. Therefore, it is of critical importance that ML models do not propagate discrimination. Collecting accurate labeled data in societal…

Machine learning (ML) algorithms have become integral to decision making in various domains, including healthcare, finance, education, and law enforcement. However, concerns about fairness and bias in these systems pose significant ethical…

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time…

There have been many papers with algorithms for improving fairness of machine-learning classifiers for tabular data. Unfortunately, most use only very few datasets for their experimental evaluation. We introduce a suite of functions for…

Machine learning (ML) is increasingly being used in high-stakes applications impacting society. Therefore, it is of critical importance that ML models do not propagate discrimination. Collecting accurate labeled data in societal…

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of helpfulness and harmlessness for question-answering pairs,…

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of…

Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it is essential to…

Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure…

We study the problem of fair binary classification using the notion of Equal Opportunity. It requires the true positive rate to distribute equally across the sensitive groups. Within this setting we show that the fair optimal classifier is…

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some…

This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…