Related papers: Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching

Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching

URL: http://arxiv.org/abs/2601.21662v1
Date: Thu, 29 Jan 2026 12:58:42 GMT
Title: Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
Authors: Li Ju, Mayank Nautiyal, Andreas Hellander, Ekta Vats, Prashant Singh,
Abstract summary: Vision-Language Models (VLMs) are typically deterministic in nature and lack intrinsic mechanisms to quantify uncertainty.<n>We theoretically motivate negative log-density of an embedding as a proxy for the epistemic uncertainty, where low-density regions signify model ignorance.<n>We empirically demonstrate that REPVLM achieves near-perfect correlation between uncertainty and prediction error, significantly outperforming existing baselines.
Score: 3.0708725114491293
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Vision-Language Models (VLMs) are typically deterministic in nature and lack intrinsic mechanisms to quantify epistemic uncertainty, which reflects the model's lack of knowledge or ignorance of its own representations. We theoretically motivate negative log-density of an embedding as a proxy for the epistemic uncertainty, where low-density regions signify model ignorance. The proposed method REPVLM computes the probability density on the hyperspherical manifold of the VLM embeddings using Riemannian Flow Matching. We empirically demonstrate that REPVLM achieves near-perfect correlation between uncertainty and prediction error, significantly outperforming existing baselines. Beyond classification, we also demonstrate that the model also provides a scalable metric for out-of-distribution detection and automated data curation.

Related papers

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning [1.9435397960631862]
Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks.<n>We show that EDL training corresponds to amortized variational inference in a hierarchical Bayesian model with a tempered pseudo-likelihood.<n>We introduce Density-Informed Pseudo-count EDL (DIP-EDL), a new parametrization that decouples class prediction from the magnitude of uncertainty.
arXiv Detail & Related papers (2026-02-01T22:57:39Z)
The Illusion of Certainty: Uncertainty quantification for LLMs fails under ambiguity [48.899855816199484]
We introduce MAQA* and AmbigQA*, the first ambiguous question-answering (QA) datasets equipped with ground-truth answer distributions.<n>We show that predictive-distribution and ensemble-based estimators are fundamentally limited under ambiguity.
arXiv Detail & Related papers (2025-11-06T14:46:35Z)
Why Machine Learning Models Fail to Fully Capture Epistemic Uncertainty [3.4970971805884474]
We make use of a more fine-grained taxonomy of epistemic uncertainty sources in machine learning models.<n>We show that high model bias can lead to misleadingly low estimates of epistemic uncertainty.<n>Common second-order uncertainty methods systematically blur bias-induced errors into aleatoric estimates.
arXiv Detail & Related papers (2025-05-29T14:50:46Z)
Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
arXiv Detail & Related papers (2024-06-05T16:35:30Z)
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities [79.9629927171974]
Uncertainty in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. We propose Kernel Language Entropy (KLE), a novel method for uncertainty estimation in white- and black-box LLMs.
arXiv Detail & Related papers (2024-05-30T12:42:05Z)
Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere [3.572499139455308]
This paper introduces a new perspective on incorporating uncertainty into contrastive learning by embedding representations within a spherical space. We leverage the concentration parameter, kappa, as a direct, interpretable measure to quantify uncertainty explicitly.
arXiv Detail & Related papers (2024-05-26T07:08:13Z)
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
arXiv Detail & Related papers (2023-11-15T05:58:35Z)
DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner. We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
arXiv Detail & Related papers (2021-02-16T23:50:35Z)
The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
arXiv Detail & Related papers (2020-12-05T17:30:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.