Conformal Prediction Sets Improve Human Decision Making

2024-01-24 · Jesse C. Cresswell, Yi Sui, Bhargava Kumar, Noël Vouitsis

In response to everyday queries, humans explicitly signal uncertainty and offer alternative answers when they are unsure. Machine learning models that output calibrated prediction sets through conformal prediction mimic this human behaviour; larger sets signal greater uncertainty while providing alternatives. In this work, we study the usefulness of conformal prediction sets as an aid for human decision making by conducting a pre-registered randomized controlled trial with conformal prediction sets provided to human subjects. With statistical significance, we find that when humans are given conformal prediction sets their accuracy on tasks improves compared to fixed-size prediction sets with the same coverage guarantee. The results show that quantifying model uncertainty with conformal prediction is helpful for human-in-the-loop decision making and human-AI teams.

📄 PDF Abstract BibTeX arXiv:2401.13744

Code (1)

layer6ai-labs/hitl-conformal-prediction 공식 구현 pytorch

Tasks

Conformal PredictionDecision Making Prediction

Conformal Prediction and Human Decision Making

2025-03-12 · Jessica Hullman, Yifan Wu, Dawei Xie, Ziyang Guo 외

Methods to quantify uncertainty in predictions from arbitrary models are in demand in high-stakes domains like medicine and finance. Conformal prediction has emerged as a popular method for producing a set of predictions…

Conformal Prediction Decision Making Prediction Uncertainty Quantification

Conformal Set-based Human-AI Complementarity with Multiple Experts

2025-08-09 · Helbert Paat, Guohao Shen arxiv

Decision support systems are designed to assist human experts in classification tasks by providing conformal prediction sets derived from a pre-trained model. This human-AI collaboration has demonstrated enhanced classif…

Towards Human-AI Complementarity with Prediction Sets

2024-05-27 · Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri 외

Decision support systems based on prediction sets have proven to be effective at helping human experts solve classification tasks. Rather than providing single-label predictions, these systems provide sets of label predi…

Conformal Prediction Prediction

Evaluating the Utility of Conformal Prediction Sets for AI-Advised Image Labeling

2024-01-16 · Dongping Zhang, Angelos Chatzimparmpas, Negar Kamali, Jessica Hullman

As deep neural networks are more commonly deployed in high-stakes domains, their black-box nature makes uncertainty quantification challenging. We investigate the presentation of conformal prediction sets--a distribution…

Conformal Prediction Decision Making Prediction Uncertainty Quantification+1

Improving Expert Predictions with Conformal Prediction

2022-01-28 · Eleni Straitouri, Lequn Wang, Nastaran Okati, Manuel Gomez Rodriguez

Automated decision support systems promise to help human experts solve multiclass classification tasks more efficiently and accurately. However, existing systems typically require experts to understand when to cede agenc…