Religious adherence reduces corporate greenwashing behavior.
problem Greenwashing behavior by corporations.
method Analysis of a large US firm sample (2005-2019), focusing on selective disclosure.
result Religious adherence correlates with lower greenwashing behavior.
This paper argues for decolonizing AI alignment by incorporating open-source Hinduism concepts.
problem Coloniality in AI development and deployment, particularly in alignment practices.
method Proposes three forms of openness: model, societal, and excluded knowledge openness, using Hindu viśe\d{s}a-dharma.
result AI alignment should be decolonialized to avoid moral absolutism and better align with desired values.
Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, w…
Reflective of income and wealth distributions, philanthropic gifting appears to follow an approximate power-law size distribution as measured by the size of gifts received by individual institutions. We explore the ecology of gifting by analysing data sets of individual gifts for a diverse group of institutions dedicat…
Paper debiases multiple word embedding biases simultaneously.
problem Reduction of multiple biases in word embeddings.
method Joint multiclass debiasing approach using Word Embeddings Association Test (WEAT).
result Demonstrates reduction or complete elimination of bias in word embeddings.
Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the training error on the available historical data. Therefore, if there is a bias related to a sensitive attribute such as gender, race, religion, e…
The paper examines challenges in achieving fair predictions using causal counterfactuals.
problem Achieving fair predictions using causal counterfactuals in fairness settings.
method Analyzes the limitations of causal models in fairness settings and the challenges of selecting counterfactuals.
result Causal models that capture counterfactuals are outside the class commonly considered in fairness literature.
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
problem Bias in machine learning classifiers due to historical discrimination or underrepresentation of minority groups.
method Integrates uplift modeling with decision trees and introduces a modified leaf relabeling approach for fairness.
result Achieves an acceptable accuracy-discrimination tradeoff while maintaining interpretability.
As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether th…
Paper proposes a method to identify and treat latent discriminating features in machine learning models.
problem Fairness issues in machine learning models trained on historical data containing sensitive attributes.
method A novel algorithm that identifies and treats latent discriminating features, agnostic of the learning algorithm.
result Experimental results show near-ideal fairness measurement compared to other methods.
Population growth (or decay) in a country can be due to various f socio-economic constraints, as demonstrated in this paper. For example, sexual intercourse is banned in various religions, during Nativity and Lent fasting periods. Data consisting of registered daily birth records for very long (35,429 points) time seri…
New fairness criterion for risk-sensitive decisions in regulated industries.
problem Ensuring equitable outcomes in risk-sensitive decision-making.
method Marginal fairness for generalized distortion risk measures, two-step decision-making process.
result Ensures fairness in decision-making under risk measures, regardless of protected attributes.
Proposes Pareto efficient fairness for supervised learning models.
problem Ensuring fairness in machine learning models without sacrificing accuracy.
method Formulates a bilevel optimization problem to find Pareto efficient classifiers.
result Guaranteed solution on Pareto frontier for convex and non-convex objectives.
FairDTD improves fairness in GNNs by distilling dual teacher knowledge, balancing utility and bias.
problem Bias in GNN predictions due to sensitive attributes.
method Dual-Teacher Distillation with a causal graph model, feature and structure teachers, and graph-level distillation.
result Achieves optimal fairness while preserving high model utility.
Study analyzes bias interactions in multimodal models using simulation-based methods.
problem Analyzing dynamic bias interactions in multimodal models to ensure fairness and equity.
method Simulation-based heuristic approach to compute bias scores for text-only, image-only, and multimodal embeddings.
result Multimodal bias interactions can be amplification, mitigation, or neutral, with text bias often dominant.
Fairness-aware learning is a novel framework for classification tasks. Like regular empirical risk minimization (ERM), it aims to learn a classifier with a low error rate, and at the same time, for the predictions of the classifier to be independent of sensitive features, such as gender, religion, race, and ethnicity. …
The paper introduces a new algorithm for fair decision-making in outcome control tasks.
problem Fair and equitable automated decision-making in outcome control tasks.
method Causal analysis and optimization to ensure fairness in decision-making.
result Developed an algorithm for maximizing Y while ensuring causal fairness. This work analyzes fairness-accuracy trade-offs using causal methods.
problem Discriminatory behavior in machine learning systems based on sensitive characteristics.
method Introduces path-specific excess loss (PSEL) and causal fairness/utility ratio to quantify trade-offs.
result Shows how enforcing fairness constraints can reduce discrimination while increasing loss.