Related papers: Mitigating Gender Bias Amplification in Distributi…
Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems. In this work, we compare two common strategies for encoding label constraints in a…
Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we examine this claim…
We develop a distribution regression model with a censored selection rule, offering a semi-parametric generalization of the Heckman selection model. Our approach applies to the entire distribution, extending beyond the mean or median,…
We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing…
Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…
The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…
We develop a novel bias mitigation framework with distribution-based fairness constraints suitable for producing demographically blind and explainable machine-learning models across a wide range of fairness levels. This is accomplished…
This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA),…
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…
Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…
Recommendation Systems (RS) are often plagued by popularity bias. When training a recommendation model on a typically long-tailed dataset, the model tends to not only inherit this bias but often exacerbate it, resulting in…
Despite widespread use in natural language processing (NLP) tasks, word embeddings have been criticized for inheriting unintended gender bias from training corpora. programmer is more closely associated with man and homemaker is more…
In recent years, the availability of large-scale annotated datasets, such as the Stanford Natural Language Inference and the Multi-Genre Natural Language Inference, coupled with the advent of pre-trained language models, has significantly…
Optimization is widely used in statistics, and often efficiently delivers point estimates on useful spaces involving structural constraints or combinatorial structure. To quantify uncertainty, Gibbs posterior exponentiates the negative loss…
Language models (LMs) exhibit and amplify many types of undesirable biases learned from the training data, including gender bias. However, we lack tools for effectively and efficiently changing this behavior without hurting general language…
While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…
Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular…
As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as…
Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of…
The Bayesian conjugate gradient method offers probabilistic solutions to linear systems but suffers from poor calibration, limiting its utility in uncertainty quantification tasks. Recent approaches leveraging postiterations to construct…