Concept

Separate model ignorance from irreducible uncertainty

Some uncertainty needs more information; some uncertainty is part of the world.

When it fits

  • An AI answer says the outcome is uncertain and you need to know what action could reduce that uncertainty.

When to avoid it

  • The two forms can coexist and model uncertainty estimates may themselves be imperfect.

The idea

Ask whether the uncertainty is epistemic—caused by limited knowledge, data or model coverage—or aleatoric—caused by inherent variability in the outcome. Epistemic uncertainty can sometimes be reduced through retrieval, measurement or expert input. Aleatoric uncertainty may require robust options, buffers or probability-aware decisions instead.

An example

Uncertainty about a current software version can be resolved by checking documentation; uncertainty about exact future demand may remain even with good data.

Check your result

The next action matches the type of uncertainty rather than asking for 'more research' indiscriminately.

Keep this limit in mind

  • The two forms can coexist and model uncertainty estimates may themselves be imperfect.

Connected ideas

Useful with
Ask what perfect information could change

Evidence and sources

Supports

Human-AI uncertainty research distinguishes aleatoric uncertainty from inherent outcome variability and epistemic uncertainty from limitations in the model's knowledge.

Real tasks can contain both forms simultaneously and the distinction may be difficult to estimate.

Balancing the Unknown: Exploring Human Reliance on AI Advice under Aleatoric and Epistemic Uncertainty · Abstract

All sources (1)