Work

Bias and Fairness in Artificial Intelligence: Detection and Mitigation Techniques

Year: 2025

Type: article

Abstract: This review paper examines the critical issues of bias and fairness in artificial intelligence, emphasizing various detection and mitigation techniques proposed in recent research. It systematically analyzes key methods such as data reweighing, adversarial debiasing, and fair representation learning, exploring their effectiveness across domains like healthcare, finance, and education. The paper highlights the ethical implications of biased AI systems and discusses the trade-offs between fairness, transparency, and model performance. By synthesizing findings from multiple studies, it provides a comprehensive overview of current challenges and suggests future directions to promote fairness, accountability, and inclusivity in AI development.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17601569

Author: Prajwal G

Language: English

Topic: Ethics and Social Impacts of AI

Subfield: Safety Research

Field: Social Sciences

Domain: Social Sciences

SDG: Reduced inequalities

Open Access status: green

OpenAlex ID: W7105679351

FWCI:

Cites:

Cited by:

Related to: