Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

By Umang Bhatt, Yunfeng Zhang, Javier Antorán, Q. Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melançon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo and 4 more. 2020

336 citations recorded by the source corpus.

Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most research into algorithmic transparency has predominantly focused on explainability. Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders. However, understanding a model's specific behavior alone might not be enough for stakeholders to gauge whether the model is wrong or lacks sufficient knowledge to solve the task at hand. In this paper, we argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. First, we discuss methods for assessing uncertainty. Then, we characterize how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. Finally, we outline methods for displaying uncertainty to stakeholders and recommend how to collect information required for incorporating uncertainty into existing ML pipelines. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness. We aim to encourage researchers and practitioners to measure, communicate, and use uncertainty as a form of transparency.

Subfields: Artificial Intelligence, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

Citations in the corpus

Getting a CLUE: A Method for Explaining Uncertainty Estimates (2020, methodology): “A transparent deep learning method should also inform stakeholders when it does not know the correct prediction (Bhatt et al., 2021).”
Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI (2022, background): “This builds greater trust in the dataset and subsequently, its publishers [10].”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, background): “…for producing explanations of individual model outputs (e.g., Koh and Liang, 2017; Lundberg and Lee, 2017; Ribeiro et al., 2016; Russell, 2019; Ustun et al., 2019) to approaches for communicating uncertainty (e.g., Bhatt et al., 2021; Dhami and Mandel, 2022; D. Wang et al., 2021) and beyond.”