mlsanityData to 7 Oct 2026

A Survey on Uncertainty Quantification Methods for Deep Learning

arXiv 2302.13425 ↗First posted 26 Feb 2023cs.LG stat.MLcited by 78

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have achieved tremendous success in computer vision, natural language processing, and scientific and engineering domains. However, DNNs can make unexpected, incorrect, yet overconfident predictions, leading to serious consequences in high-stakes applications such as autonomous driving, medical diagnosis, and disaster response. Uncertainty quantification (UQ) estimates the confidence of DNN predictions in addition to their accuracy. In recent years, many UQ methods have been developed for DNNs. It is valuable to systematically categorize these methods and compare their strengths and limitations. Existing surveys mostly categorize UQ methodologies by neural network architecture or Bayesian formulation, while overlooking the uncertainty sources each method addresses, making it difficult to select an appropriate approach in practice. To fill this gap, this paper presents a taxonomy of UQ methods for DNNs based on uncertainty sources (e.g., data versus model uncertainty). We summarize the advantages and disadvantages of each category, and illustrate how UQ can be applied to machine learning problems (e.g., active learning, out-of-distribution robustness, and deep reinforcement learning). We also identify future research directions, including UQ for large language models (LLMs), AI-driven scientific simulations, and deep neural networks with structured outputs.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 86 of its 241 references that are in the map. First posted on arXiv 26 Feb 2023.

Builds on

86 of 241 references.

References · 86

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2016Variational Inference: A Review for Statisticianscited by 1,466
  12. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
38 more
  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  2. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  3. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  4. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  5. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  6. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  7. 2021Characterizing possible failure modes in physics-informed neural networkscited by 632
  8. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  9. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  10. 2020A Survey of Deep Active Learningcited by 547
  11. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 464
  12. 2019Measuring Calibration in Deep Learningcited by 443
  13. 2015Deep Kernel Learningcited by 440
  14. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
  15. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  16. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  17. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  18. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  19. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
  20. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
  21. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  22. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  23. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  24. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 197
  25. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  26. 2015Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)cited by 175
  27. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  28. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  29. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  30. 2022Adaptive Conformal Predictions for Time Seriescited by 155
  31. 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 149
  32. 2020Data Uncertainty Learning in Face Recognitioncited by 134
  33. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  34. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  35. 2018Adversarial Uncertainty Quantification in Physics-Informed Neural Networkscited by 120
  36. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  37. 2021Dropout Q-Functions for Doubly Efficient Reinforcement Learningcited by 108
  38. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 31; 2026: 37.

78 papers.

Sort:

By area:

  1. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  2. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  3. 2023Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivitycited by 13
  4. 2024Graph-based Confidence Calibration for Large Language Modelscited by 10
  5. 2025Epistemic Uncertainty in Conformal Scores: A Unified Approachcited by 9
  6. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluationscited by 8
  7. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  8. 2023Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scalecited by 6
  9. 2024Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Modelscited by 6
  10. 2023Validation of uncertainty quantification metrics: a primer based on the consistency and adaptivity conceptscited by 5
  11. 2025Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?cited by 5
  12. 2026ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agentscited by 5
38 more
  1. 2025Evidential Uncertainty Estimation for Multi-Modal Trajectory Predictioncited by 4
  2. 2025A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planningcited by 4
  3. 2025Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguitycited by 4
  4. 2024Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehiclescited by 3
  5. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  6. 2026Uncertainty in a Single Pass: A Closed-Form Identity for One-Step Flow Matchingcited by 2
  7. 2023Deep Learning for Spatiotemporal Big Data: A Vision on Opportunities and Challengescited by 1
  8. 2023Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagerycited by 1
  9. 2024Uncertainty Quantification for Deep Learningcited by 1
  10. 2025Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptionscited by 1
  11. 2025Polymer Data Challenges in the AI Era: Bridging Gaps for Next-Generation Energy Materialscited by 1
  12. 2025Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operatorscited by 1
  13. 2025Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learningcited by 1
  14. 2025Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantificationcited by 1
  15. 2025Deep Learning-Based Analysis of Power Consumption in Gasoline, Electric, and Hybrid Vehiclescited by 1
  16. 2025Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Modelscited by 1
  17. 2025Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecastingcited by 1
  18. 2025Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigationcited by 1
  19. 2025Bayesian Topological Convolutional Neural Netscited by 1
  20. 2025A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysiscited by 1
  21. 2025Multivariate Uncertainty Quantification with Tomographic Quantile Forestscited by 1
  22. 2026PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learningcited by 1
  23. 2026UQ-SHRED: uncertainty quantification of shallow recurrent decoder networks for sparse sensing via engressioncited by 1
  24. 2026Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Datasetcited by 1
  25. 2025MMformer with Adaptive Transferable Attention: Advancing Multivariate Time Series Forecasting for Environmental Applicationscited by 0
  26. 2025Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compressioncited by 0
  27. 2025Programmable Virtual Humans Toward Human Physiologically-Based Drug Discoverycited by 0
  28. 2025A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Modelscited by 0
  29. 2025A Simple and Effective Method for Uncertainty Quantification and OOD Detectioncited by 0
  30. 2025Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AIcited by 0
  31. 2025Negation-Aware Weighted Information Fusion for Reliable Evidential Reasoningcited by 0
  32. 2025Towards Human-Centric Intelligent Treatment Planning for Radiation Therapycited by 0
  33. 2025Dataset Safety in Autonomous Driving: Requirements, Risks, and Assurancecited by 0
  34. 2025Deep Learning for Primordial B-mode Extractioncited by 0
  35. 2026RAG: A Random-Forest-Based Generative Design Framework for Uncertainty-Aware Design of Metamaterials with Complex Functional Response Requirementscited by 0
  36. 2026Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learningcited by 0
  37. 2026Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibrationcited by 0
  38. 2026Conditional Uncertainty-Aware Political Deepfake Detection with Stochastic Convolutional Neural Networkscited by 0

50 most cited of 78 All 78 (JSON)