Related papers: Fair Embedding Engine: A Library for Analyzing and…
Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demonstrated the existence…
Machine learning models are central to people's lives and impact society in ways as fundamental as determining how people access information. The gravity of these models imparts a responsibility to model developers to ensure that they are…
Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this…
Training ML models which are fair across different demographic groups is of critical importance due to the increased integration of ML in crucial decision-making scenarios such as healthcare and recruitment. Federated learning has been…
Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…
Bias can be introduced in diverse ways in machine learning datasets, for example via selection or label bias. Although these bias types in themselves have an influence on important aspects of fair machine learning, their different impact…
Embedding models are integral to AI applications like semantic search, personalized recommendations, and retrieval augmented generation for LLMs, necessitating high-quality training data. However, the limited scalability of manual data…
Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…
Gender bias in word embeddings gradually becomes a vivid research field in recent years. Most studies in this field aim at measurement and debiasing methods with English as the target language. This paper investigates gender bias in static…
The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial features from a large number of…
Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always…
Multiple measures, such as WEAT or MAC, attempt to quantify the magnitude of bias present in word embeddings in terms of a single-number metric. However, such metrics and the related statistical significance calculations rely on treating…
Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often…
With the development of community based question answering (Q&A) services, a large scale of Q&A archives have been accumulated and are an important information and knowledge resource on the web. Question and answer matching has been…
Artificial Intelligence (AI) is at the forefront of modern technology, and its effects are felt in many areas of society. To prevent algorithmic disparities, fairness, accountability, transparency, and ethics (FATE) in AI are being…
The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…
Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of machine learning with far-reaching societal impact.…
The rapid advancement of Language Model technologies has opened new opportunities, but also introduced new challenges related to bias and fairness. This paper explores the uncharted territory of potential biases in state-of-the-art…
Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes…