Maintaining The Humanity of Our Models

TL;DR

This paper emphasizes the importance of maintaining human values in AI and ML models by promoting interpretability, addressing human biases, and ensuring transparency about societal impacts as these technologies become more integrated into daily life.

Contribution

It advocates for rigorous standards in interpretability, bias consideration, and transparency to preserve human-centric values in AI and ML development.

Findings

Need for standardized interpretability metrics

Importance of addressing human biases in data

Call for transparent societal impact assessments

Abstract

Artificial intelligence and machine learning have been major research interests in computer science for the better part of the last few decades. However, all too recently, both AI and ML have rapidly grown to be media frenzies, pressuring companies and researchers to claim they use these technologies. As ML continues to percolate into daily life, we, as computer scientists and machine learning researchers, are responsible for ensuring we clearly convey the extent of our work and the humanity of our models. Regularizing ML for mass adoption requires a rigorous standard for model interpretability, a deep consideration for human bias in data, and a transparent understanding of a model's societal effects.