Knowledge Tree
uncertainty
Facts (23)
Sources
A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Dec 9, 2025 6 facts
referenceL. Smith and Yarin Gal proposed using measures of uncertainty for adversarial example detection in their 2018 arXiv preprint 'Understanding measures of uncertainty for adversarial example detection'.
referenceFakour, Mosleh, and Ramezani published a structured review of literature concerning uncertainty in machine learning and deep learning in 2024.
referenceJ. Gawlikowski, C.R.N. Tassi, M. Ali, J. Lee, M. Humt, J. Feng, A. Kruspe, R. Triebel, P. Jung, and R. Roscher published 'A survey of uncertainty in deep neural networks' in the journal Artificial Intelligence Review in 2023.
referenceIncorvaia, Hond, and Asgari utilized anomaly-based dataset dissimilarity measures to quantify the uncertainty of machine learning model performance in their 2024 paper.
referenceThe paper 'A Comprehensive Review of Neuro-symbolic AI for Robustness' reviews techniques for modeling robustness, quantifying uncertainty, and enabling intervenability, while examining how logic, probability, and learning can be integrated into unified or modular architectures to support transparent, adaptive reasoning.
referenceChrysos et al. identified quantifying uncertainty and hallucination in foundation models as the next frontier in reliable AI in their 2025 ICLR workshop proposal.
Construction of intelligent decision support systems through ... - Nature nature.com Oct 10, 2025 4 facts
measurementIn healthcare resource allocation scenarios, the IKEDS framework achieved a 9.2% accuracy advantage over the best baseline, particularly for scenarios involving allocation under uncertainty.
claimThe performance advantage of the IKEDS framework increases with higher levels of knowledge complexity, uncertainty, and cross-domain requirements.
measurementThe IKEDS framework achieves an average 21.8% improvement in scenarios with significant uncertainty by combining structured knowledge representation with flexible generation to handle incomplete information.
claimThe IKEDS framework provides value in resource allocation under uncertainty by reasoning explicitly about uncertainty while maintaining clear connections to organizational priorities.
Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org Feb 16, 2025 2 facts
claimMulti-agent frameworks integrated with neuro-symbolic methods provide advantages in handling uncertainty, fostering collaboration, and maintaining resilience in dynamic environments.
referenceAlexander I Cowen-Rivers, Pasquale Minervini, Tim Rocktaschel, Matko Bosnjak, Sebastian Riedel, and Jun Wang authored the paper 'Neural variational inference for estimating uncertainty in knowledge graph embeddings', published as an arXiv preprint in 2019.
A Survey on the Theory and Mechanism of Large Language Models arxiv.org Mar 12, 2026 2 facts
procedureKim and Hospedales (2025) proposed a stochastic bi-level optimization algorithm that utilizes Langevin dynamics to manage uncertainty and non-convexity in hyperparameter landscapes.
referenceThe research paper 'Do not abstain! identify and solve the uncertainty' was published as an arXiv preprint (arXiv:2509.21473) and cited in section 7.2.2 of the survey.
EdinburghNLP/awesome-hallucination-detection - GitHub github.com 2 facts
measurementEvaluation of uncertainty and confidence in language models uses AUROC, AUARC, NumSet, Deg, and EigV as metrics, and utilizes datasets including CoQA, TriviaQA, and Natural Questions.
claimImproved sequence likelihood, defined as the log probability of a generated sequence, is used in confidence or uncertainty computation for AI systems.
Psychedelics, Sociality, and Human Evolution frontiersin.org 1 fact
claimPsychedelic-assisted divination practices may provide access to new perspectives and unconscious knowledge, serving as a coping strategy against uncertainty.
Quantum Approaches to Consciousness plato.stanford.edu Nov 30, 2004 1 fact
referenceA. Tversky and E. Shafir authored the 1992 paper 'The disjunction effect in choice under uncertainty', published in Psychological Science, volume 3, pages 305–309.
LLM Hallucination Detection and Mitigation: State of the Art in 2026 zylos.ai Jan 27, 2026 1 fact
referenceA Medium article titled 'Quantifying LLMs Uncertainty with Confidence Scores' discusses techniques for using confidence scores to measure uncertainty in large language models.
Papers - Dr Vaishak Belle vaishakbelle.github.io 1 fact
referenceI. Papantonis and Vaishak Belle authored the paper 'Why not both? Complementing explanations with uncertainty, and self-confidence in human-AI collaboration', published in Frontiers in Computer Science in 2025.
Neuro symbiotic AI: The Future of Human-Machine Collaboration medium.com Nov 2, 2025 1 fact
claimUnifying logic-based symbolic reasoning with neural learning improves the ability of artificial intelligence systems to handle uncertainty.
A Knowledge Graph-Based Hallucination Benchmark for Evaluating ... arxiv.org Feb 23, 2026 1 fact
claimThe framework assigns one point to abstained responses, providing partial credit for appropriately expressing uncertainty or lack of knowledge, as supported by Kalai et al. (2025).
Building Trustworthy NeuroSymbolic AI Systems - arXiv arxiv.org 1 fact
referenceLin, Hilton, and Evans (2022) published 'Teaching Models to Express Their Uncertainty in Words' in Transactions on Machine Learning Research.