FairBED quantifies dataset fairness as uninformative about sensitive attributes and uses fairness-aware BED to gather data yielding better fairness-accuracy trade-offs than random or standard BED acquisition.
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license {https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.
representative citing papers
Introduces Situated Interaction Auditing (SIA) to examine how user sociodemographic signals affect LLM response quality, content, and tone in personal interactions.
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
TIRA attacks with PMiS and PRSMP push fairness metrics to ideal values and reduce SHAP attribution for protected features to zero in black-box settings.
Causal fuzzing with budgeted interventions can detect residual direct and indirect influence of unlearned data that standard attribution methods miss due to proxies, cancellations, and masking.
Differential parity is proposed as a relative fairness metric between decision sets independent of sensitive attributes, usable with or without a reference set and extendable via ML for mismatched data.
FairLogue provides modular tools to quantify intersectional fairness gaps in clinical ML using extended demographic parity, equalized odds, and counterfactual methods, shown on a glaucoma surgery prediction task from All of Us data.
Proposes a behavioral model of positive friction to characterize beneficial obstacles in AI user experiences and developer processes, diagnose needs, and suggest design solutions.
InsightBoard integrates synchronized multi-metric plots, correlation analysis, and group fairness indicators into TensorBoard to reveal subgroup disparities that aggregate metrics hide during model training.
citing papers explorer
-
Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research
Introduces Situated Interaction Auditing (SIA) to examine how user sociodemographic signals affect LLM response quality, content, and tone in personal interactions.