Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models
Not on the map. Why?
Abstract (arXiv)
In the critical task of making generative models trustworthy and robust, methods for Uncertainty Quantification (UQ) have begun to show encouraging potential. However, many of these methods rely on rigid heuristics that fail to generalize across tasks and modalities. Here, we propose a novel framework for UQ that is highly flexible and approaches or surpasses the performance of prior heuristic methods. We introduce Directional Concentration Uncertainty (DCU), a novel statistical procedure for quantifying the concentration of embeddings based on the von Mises-Fisher (vMF) distribution. Our method captures uncertainty by measuring the geometric dispersion of multiple generated outputs from a language model using continuous embeddings of the generated outputs without any task specific heuristics. In our experiments, we show that DCU matches or exceeds calibration levels of prior works like semantic entropy (Kuhn et al., 2023) and also generalizes well to more complex tasks in multi-modal domains. We present a framework for the wider potential of DCU and its implications for integration into UQ for multi-modal and agentic frameworks.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 4 Feb 2026.
Builds on
18 of 25 references.
References · 18
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
- 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
- 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
- 2023Conformal Language Modelingcited by 163
- 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
- 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
- 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
- 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
- 2024SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Modelscited by 54
6 more
- 2024Uncertainty Quantification for In-Context Learning of Large Language Modelscited by 45
- 2024Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinationscited by 38
- 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 36
- 2024Non-Exchangeable Conformal Language Generation with Nearest Neighborscited by 21
- 2024Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answeringcited by 20
- 2025Towards Transparent AI: A Survey on Explainable Language Modelscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Score-based generative models are provably robust: an uncertainty quantification perspective
- 2026Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking
- 2026Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning
- 2025Generative Uncertainty in Diffusion Models
- 2026The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models
- 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
- 2026Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
- 2026Uncertainty Quantification for Large Language Diffusion Models