mlsanityData to 14 Oct 2026

Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'

arXiv 2505.04950 ↗First posted 8 May 2025cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Despite AI's impressive achievements, including recent advances in generative and large language models, there remains a significant gap in the ability of AI systems to handle uncertainty and generalize beyond their training data. AI models consistently fail to make robust enough predictions when facing unfamiliar or adversarial data. Traditional machine learning approaches struggle to address this issue, due to an overemphasis on data fitting, while current uncertainty quantification approaches suffer from serious limitations. This position paper posits a paradigm shift towards epistemic artificial intelligence, emphasizing the need for models to learn from what they know while at the same time acknowledging their ignorance, using the mathematics of second-order uncertainty measures. This approach, which leverages the expressive power of such measures to efficiently manage uncertainty, offers an effective way to improve the resilience and robustness of AI systems, allowing them to better handle unpredictable real-world environments.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 119 of its 261 references that are in the map. First posted on arXiv 8 May 2025.

Builds on

119 of 261 references.

References · 119

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2017On Calibration of Modern Neural Networkscited by 4,960
  10. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  11. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  12. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
38 more
  1. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  3. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2016Concrete Problems in AI Safetycited by 1,642
  6. 2019Natural Adversarial Examplescited by 1,408
  7. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  8. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  11. 2023PaLM 2 Technical Reportcited by 1,162
  12. 2018Experience Replay for Continual Learningcited by 1,095
  13. 2020In Search of Lost Domain Generalizationcited by 1,054
  14. 2016End to End Learning for Self-Driving Carscited by 1,009
  15. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  16. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  17. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  18. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  19. 2013Domain Generalization via Invariant Feature Representationcited by 623
  20. 2019Three scenarios for continual learningcited by 614
  21. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 588
  22. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  23. 2017Minimax Regret Bounds for Reinforcement Learningcited by 503
  24. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  25. 2017Robust Adversarial Reinforcement Learningcited by 451
  26. 2019Measuring Calibration in Deep Learningcited by 446
  27. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
  28. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 394
  29. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  30. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
  31. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  32. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  33. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  34. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  35. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  36. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  37. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 200
  38. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200

50 most cited of 119 All 119 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Epistemic Generative Adversarial Networkscited by 4
  2. 2026Statistical inference with belief functions: A surveycited by 2
  3. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  4. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  5. 2026What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamicscited by 1
  6. 2026Decision-Aligned Evaluation of Uncertainty Quantificationcited by 1
  7. 2026Conformalised imprecise inference for robust extrapolation under limited datacited by 0
  8. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0