Complementarity without ground truth?
Organizations: Institute of Biomedical Ethics and History of Medicine, University of Zürich, Zürich, Switzerland · SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA), Lugano, Switzerland · ETH Zürich, Zürich, Switzerland · Management in Networked and Digital Societies (MINDS) Department, Kozminski University, Warsaw, Poland ·
Abstract
Human-AI complementarity captures the idea that a human assisted by an AI system can outperform both the human and the AI acting alone. In prediction tasks, this improvement is assessed against ground truth labels produced through a reference construction procedure and intended to represent the state of affairs to be predicted. Many human-AI interactions, including those where medical AI provides treatment recommendations, however, concern tasks other than predicting what obtains. Their relevant output concerns adequacy relative to a practical goal and depends on several evaluative dimensions. In this work, we examine the ground truth dependence of complementarity and extend it to human-AI interactions where ground truth is not the appropriate reference. We show that tasks beyond prediction can still admit a reference construction procedure that generates adequacy labels. We develop a route for extending complementarity to such settings. It replaces ground truth labels with context-dependent adequacy labels generated through a two-step scoring methodology inspired by multi-criteria decision analysis frameworks in healthcare and it makes the normative choices underlying reference construction explicit. Because the construction of adequacy labels embeds evaluative choices, we draw methodological inspiration from computational reliabilism to identify technical, scientific, and social factors relevant to supporting their construction. Our approach expands the empirical study of human-AI complementarity beyond prediction tasks, enabling its quantitative evaluation in decision-support settings where ground truth is not the appropriate evaluative reference.
Figures & tables
| Concept | Definition | Measure | Functional form | Loss / performance basis | Source |
|---|---|---|---|---|---|
| Human–machine collaboration | Algorithmic output informs a human who retains the final judgment. | Joint performance | No functional is introduced; performance is compared across human-only, AI-assisted, and related conditions. | Empirical performance comparison; typically label-based task performance. | Vaccaro and Waldo (2019) |
| Human–machine complementarity | Human and machine capabilities are combined so that team performance can exceed either alone. | Team utility/loss | Joint objective for team performance | Explicit loss / utility-based formulation. | Wilder et al. (2020) |
| Complementary team performance | The human–AI team outperforms both the human and AI alone. | CTP | . | Accuracy-based; equivalent to - loss on labelled tasks. | Bansal et al. (2021b) |
| Complementarity | The combined human–algorithm system has lower expected loss than either component alone. | Expected-loss gain | . | Explicit loss-based formulation. | Donahue et al. (2022) |
| Human–AI complementarity | Joint decision-making produces performance beyond the human- and AI-alone baselines. | Joint accuracy | compared with and . | Accuracy-based; equivalent to - -loss comparison. | Inkpen et al. (2023) |
| Human–AI collaboration protocols | Different protocols determine how human and AI judgments form the final diagnosis. | Diagnostic performance | No functional; protocols are compared through team diagnostic performance. | Accuracy and related diagnostic metrics on labelled medical tasks. | Cabitza et al. (2023) |