AI & ML
Miscalibrated AI improves human calibration: An alignment problem for AI-assisted Decision education
arXiv cs.HC0 views
arXiv:2611.23618v1 Announce Type: new Abstract: Using artificial intelligence (AI) well requires probabilistic thinking, and central to it is calibration: expressing certainty that matches one's actual accuracy. Calibration is a decision skill, but a notoriously difficult one to teach. Because AI systems typically generate a probability alongside every prediction, observing these probabilities may help humans learn to provide better calibrated judgments. This is one form of what we call AI-assisted decision education -- using AI to teach the judgment skills that decision-making requires -- of which learning by observation, as here, is among the simplest forms. In a preregistered experiment, novice participants (N = 300) judged the probability that images of white blood cells were cancerous, before and after exposure to a highly accurate (94%) convolutional neural network. A single model was shown in three ways, holding accuracy fixed while varying the certainty it expressed: its original probabilities, which were conservative and poorly calibrated for the model's accuracy; a recalibrated version, well calibrated for the model and correspondingly certain; or categorical predictions carrying no probability information. When later tested without the AI, only the original, conservative display improved participants' calibration. It did so by reducing over-extremity, without a condition-specific improvement in discrimination. Notably, the display that taught best was the one miscalibrated for the model. AI-assisted decision education therefore faces an alignment problem: the signal that best describes a model, need not be the signal that best supports the learner.
Source:https://arxiv.org/abs/2611.23618PreviousSmart Glasses for Ubiquitous Computing: A Layered Survey and the Road AheadNextMEM-STRESS: Longitudinal Field Study of a Wearable-Informed AI Chatbot for Stress Management
Related posts
Fiona the Hippo Died After Eating a Hat. But How Does a Hat Kill a Hippo?
0Wired

Why ChatGPT Cites Review Sites Instead of Your Company Website
0dev.to
Basalt walkthrough is up: why 776 tok/s needs the whole card to itself
0dev.to
Introducing AWS RTB Fabric Modules available through AWS Marketplace: AdTech partner intelligence, inline in the bid path
0AWS for Industries
What Is Docs-as-Code? A Plain-English Guide
0dev.to GitHub
Phân tích dữ liệu vòng 10 Bundesliga: Frankfurt và Hoffenheim cạnh tranh bước ngoặt điểm số
0dev.to Data