Conformal Prediction Sets Improve Human Decision Making
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 28 of its 64 references that are in the map. First posted on arXiv 24 Jan 2024.
Builds on
28 of 64 references.
References · 28
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
16 more
- 2020Classification with Valid and Adaptive Coveragecited by 396
- 2021Revisiting the Calibration of Modern Neural Networkscited by 390
- 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
- 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 308
- 2021A Survey of Human-in-the-loop for Machine Learningcited by 215
- 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
- 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
- 2022Adaptive Conformal Predictions for Time Seriescited by 161
- 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 152
- 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
- 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
- 2022Improving Expert Predictions with Conformal Predictioncited by 54
- 2021Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classificationcited by 39
- 2022On the Utility of Prediction Sets in Human-AI Teamscited by 34
- 2021Set-valued classification -- overview via a unified frameworkcited by 27
- 2023Designing Decision Support Systems Using Counterfactual Prediction Setscited by 26
Built on by
Citing papers per year: 2024: 13; 2025: 13; 2026: 9.
35 papers.
Sort:
By area:
- 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
- 2024Length Optimization in Conformal Predictioncited by 39
- 2024Towards Human-AI Complementarity with Prediction Setscited by 25
- 2024Conformal Prediction: A Data Perspectivecited by 25
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Modelscited by 19
- 2024Conformal Prediction Sets Can Cause Disparate Impactcited by 14
- 2024The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignmentcited by 13
- 2024Does confidence calibration improve conformal prediction?cited by 12
- 2024Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregationcited by 9
- 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Setscited by 9
- 2025Conformal Prediction and Human Decision Makingcited by 9
- 2025Document Summarization with Conformal Importance Guaranteescited by 6
23 more
- 2025Exploring the Noise Robustness of Online Conformal Predictioncited by 5
- 2025Robust Conformal Prediction with a Single Binary Certificatecited by 4
- 2026Conformal Agent Error Attributioncited by 4
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Predictioncited by 3
- 2025Test-time augmentation improves efficiency in conformal predictioncited by 3
- 2024Conformal Risk Control for Pulmonary Nodule Detectioncited by 2
- 2025No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Predictioncited by 2
- 2025Counterfactually Fair Conformal Predictioncited by 2
- 2024A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessmentcited by 1
- 2025Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Scorecited by 1
- 2025Performance of Conformal Prediction in Capturing Aleatoric Uncertaintycited by 1
- 2026Elements of Conformal Predictioncited by 1
- 2026On the Burden of Achieving Fairness in Conformal Predictioncited by 1
- 2026A Framework for Measuring Appropriate Reliance on Set-Valued AI Advicecited by 1
- 2026Localized Conformal Prediction for Image Classification with Vision-Language Modelscited by 1
- 2024An Empirical Examination of the Evaluative AI Frameworkcited by 0
- 2025Conformal Predictions for Human Action Recognition with Vision-Language Modelscited by 0
- 2025Parameter Space Analysis through Guided Visual Interpolationscited by 0
- 2025Conformal Correction for Efficiency May be at Odds with Entropycited by 0
- 2026Distribution-Free Robust Predict-Then-Optimize in Function Spacescited by 0
- 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
- 2026Uncertainty of Vision Medical Foundation Modelscited by 0
- 2026Should I stay or should I show? Learning to selectively disclose informationcited by 0
- 2026Should I stay or should I show? Learning to selectively disclose information30 Sep 2026
- 2026Uncertainty of Vision Medical Foundation Models31 Aug 2026
- 2026Localized Conformal Prediction for Image Classification with Vision-Language Models30 Jun 2026
- 2026A Framework for Measuring Appropriate Reliance on Set-Valued AI Advice4 Jun 2026
- 2026On the Burden of Achieving Fairness in Conformal Prediction14 May 2026
- 2026Conformal Agent Error Attribution7 May 2026
- 2026Elements of Conformal Prediction25 Mar 2026
- 2026Softmax is not Enough (for Adaptive Conformal Classification)23 Feb 2026
- 2026Distribution-Free Robust Predict-Then-Optimize in Function Spaces9 Feb 2026
- 2025Conformal Correction for Efficiency May be at Odds with Entropy2 Dec 2025
- 2025Counterfactually Fair Conformal Prediction9 Oct 2025
- 2025Document Summarization with Conformal Importance Guarantees24 Sep 2025
23 more
- 2025Parameter Space Analysis through Guided Visual Interpolations23 Sep 2025
- 2025No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Prediction16 Sep 2025
- 2025Performance of Conformal Prediction in Capturing Aleatoric Uncertainty6 Sep 2025
- 2025Test-time augmentation improves efficiency in conformal prediction28 May 2025
- 2025Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score27 May 2025
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction24 Apr 2025
- 2025Conformal Prediction and Human Decision Making12 Mar 2025
- 2025Robust Conformal Prediction with a Single Binary Certificate7 Mar 2025
- 2025Conformal Predictions for Human Action Recognition with Vision-Language Models10 Feb 2025
- 2025Exploring the Noise Robustness of Online Conformal Prediction30 Jan 2025
- 2024Conformal Risk Control for Pulmonary Nodule Detection28 Dec 2024
- 2024The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment21 Dec 2024
- 2024An Empirical Examination of the Evaluative AI Framework13 Nov 2024
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models10 Oct 2024
- 2024Conformal Prediction: A Data Perspective9 Oct 2024
- 2024Conformal Prediction Sets Can Cause Disparate Impact2 Oct 2024
- 2024A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessment2 Aug 2024
- 2024Length Optimization in Conformal Prediction27 Jun 2024
- 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets10 Jun 2024
- 2024Towards Human-AI Complementarity with Prediction Sets27 May 2024
- 2024Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation25 May 2024
- 2024Conformal Prediction for Natural Language Processing: A Survey3 May 2024
- 2024Does confidence calibration improve conformal prediction?6 Feb 2024
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Modelscited by 19
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Predictioncited by 3
- 2026Localized Conformal Prediction for Image Classification with Vision-Language Modelscited by 1
- 2025Conformal Predictions for Human Action Recognition with Vision-Language Modelscited by 0
- 2026Localized Conformal Prediction for Image Classification with Vision-Language Models30 Jun 2026
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction24 Apr 2025
- 2025Conformal Predictions for Human Action Recognition with Vision-Language Models10 Feb 2025
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models10 Oct 2024
- 2026Conformal Agent Error Attributioncited by 4
- 2026Conformal Agent Error Attribution7 May 2026
- 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
- 2024Length Optimization in Conformal Predictioncited by 39
- 2024Towards Human-AI Complementarity with Prediction Setscited by 25
- 2024Conformal Prediction: A Data Perspectivecited by 25
- 2024Conformal Prediction Sets Can Cause Disparate Impactcited by 14
- 2024Does confidence calibration improve conformal prediction?cited by 12
- 2024Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregationcited by 9
- 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Setscited by 9
- 2025Conformal Prediction and Human Decision Makingcited by 9
- 2025Document Summarization with Conformal Importance Guaranteescited by 6
- 2025Exploring the Noise Robustness of Online Conformal Predictioncited by 5
- 2025Robust Conformal Prediction with a Single Binary Certificatecited by 4
12 most cited of 29 All 29 (JSON)
- 2026Should I stay or should I show? Learning to selectively disclose information30 Sep 2026
- 2026Uncertainty of Vision Medical Foundation Models31 Aug 2026
- 2026A Framework for Measuring Appropriate Reliance on Set-Valued AI Advice4 Jun 2026
- 2026On the Burden of Achieving Fairness in Conformal Prediction14 May 2026
- 2026Elements of Conformal Prediction25 Mar 2026
- 2026Softmax is not Enough (for Adaptive Conformal Classification)23 Feb 2026
- 2026Distribution-Free Robust Predict-Then-Optimize in Function Spaces9 Feb 2026
- 2025Conformal Correction for Efficiency May be at Odds with Entropy2 Dec 2025
- 2025Counterfactually Fair Conformal Prediction9 Oct 2025
- 2025Document Summarization with Conformal Importance Guarantees24 Sep 2025
- 2025Parameter Space Analysis through Guided Visual Interpolations23 Sep 2025
- 2025No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Prediction16 Sep 2025
12 newest of 29 All 29 (JSON)