Credal Concept Bottleneck Models: Structural Separation of Epistemic and Aleatoric Uncertainty

2026-02-11

AI Summary

Existing methods struggle to effectively disentangle epistemic uncertainty (model ignorance) from aleatoric uncertainty (data noise), often resulting in semantic conflation and high correlation between the two. This work proposes a Variational Faithful Concept Bottleneck Model that, for the first time, achieves architectural-level separation of these uncertainties through geometric structure: epistemic uncertainty is modeled by the size of a faithful set, while aleatoric uncertainty is captured by the distributional noise within the set. Independent optimization pathways and disjoint objectives are introduced to enforce decoupling. Evaluated on multi-annotator benchmarks, the method reduces the correlation between the two uncertainties by over an order of magnitude and significantly improves alignment—epistemic uncertainty with prediction error and aleatoric uncertainty with annotation ambiguity.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Decomposing predictive uncertainty into epistemic (model ignorance) and aleatoric (data ambiguity) components is central to reliable decision making, yet most methods estimate both from the same predictive distribution. Recent empirical and theoretical results show these estimates are typically strongly correlated, so changes in predictive spread simultaneously affect both components and blur their semantics. We propose a credal-set formulation in which uncertainty is represented as a set of predictive distributions, so that epistemic and aleatoric uncertainty correspond to distinct geometric properties: the size of the set versus the noise within its elements. We instantiate this idea in a Variational Credal Concept Bottleneck Model with two disjoint uncertainty heads trained by disjoint objectives and non-overlapping gradient paths, yielding separation by construction rather than post hoc decomposition. Across multi-annotator benchmarks, our approach reduces the correlation between epistemic and aleatoric uncertainty by over an order of magnitude compared to standard methods, while improving the alignment of epistemic uncertainty with prediction error and aleatoric uncertainty with ground-truth ambiguity.

Problem

• epistemic uncertainty
• aleatoric uncertainty
• predictive uncertainty
• uncertainty decomposition
• credal sets

Innovation

• Credal Concept Bottleneck Model
• Epistemic Uncertainty
• Aleatoric Uncertainty
• Structural Separation
• Variational Credal Set