Imagen de Portada

Can Linear Probes Measure LLM Uncertainty?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dakhmouche, Ramzi, Letellier, Adrien, Gorji, Hossein
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Numerical Analysis Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws
por: Dakhmouche, Ramzi, et al.
Publicado: (2025)

Linear cost and exponentially convergent approximation of Gaussian Matérn processes on intervals
por: Bolin, David, et al.
Publicado: (2024)

Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity
por: Luo, Hengrui, et al.
Publicado: (2026)

Enabling stratified sampling in high dimensions via nonlinear dimensionality reduction
por: Geraci, Gianluca, et al.
Publicado: (2025)

Towards Sharp Minimax Risk Bounds for Operator Learning
por: Adcock, Ben, et al.
Publicado: (2025)

Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
por: Li, Gen, et al.
Publicado: (2025)

Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks
por: Yakovlev, Konstantin, et al.
Publicado: (2025)

Faster Diffusion Models via Higher-Order Approximation
por: Li, Gen, et al.
Publicado: (2025)

On Spectral Learning for Odeco Tensors: Perturbation, Initialization, and Algorithms
por: Auddy, Arnab, et al.
Publicado: (2025)

Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications
por: Feng, Jinchao, et al.
Publicado: (2025)

Optimal Recovery Meets Minimax Estimation
por: DeVore, Ronald, et al.
Publicado: (2025)

Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights
por: Shen, Zhaiming, et al.
Publicado: (2025)

Posterior Covariance Structures in Gaussian Processes
por: Cai, Difeng, et al.
Publicado: (2024)

Gaussian Process Regression under Computational and Epistemic Misspecification
por: Sanz-Alonso, Daniel, et al.
Publicado: (2023)

Convergence Rates for Learning Pseudo-Differential Operators
por: Chen, Jiaheng, et al.
Publicado: (2026)

Solving PDEs on Spheres with Physics-Informed Convolutional Neural Networks
por: Lei, Guanhang, et al.
Publicado: (2023)

Score Operator Newton transport
por: Chandramoorthy, Nisha, et al.
Publicado: (2023)

Weighted least-squares approximation with determinantal point processes and generalized volume sampling
por: Nouy, Anthony, et al.
Publicado: (2023)

Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
por: Zhao, Yuxuan, et al.
Publicado: (2026)

A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
por: Yang, Jia-Qi, et al.
Publicado: (2025)

Which Spaces can be Embedded in $L_p$-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy
por: Lu, Yiping, et al.
Publicado: (2024)

Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias
por: Wong, Honam, et al.
Publicado: (2024)

Gaussian Processes and Reproducing Kernels: Connections and Equivalences
por: Kanagawa, Motonobu, et al.
Publicado: (2025)

Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
por: Tang, Runshi, et al.
Publicado: (2025)

Provable Diffusion Posterior Sampling for Bayesian Inversion
por: Chang, Jinyuan, et al.
Publicado: (2025)

Stein transport for Bayesian inference
por: Nüsken, Nikolas
Publicado: (2024)

Samplet limits and multiwavelets
por: Giacchi, Gianluca, et al.
Publicado: (2026)

Analysis of singular subspaces under random perturbations
por: Wang, Ke
Publicado: (2024)

Tensor Methods in High Dimensional Data Analysis: Opportunities and Challenges
por: Auddy, Arnab, et al.
Publicado: (2024)

Perturbation Analysis of Randomized SVD and its Applications to Statistics
por: Zhang, Yichi, et al.
Publicado: (2022)

Convergence of Kinetic Langevin Monte Carlo on Lie groups
por: Kong, Lingkai, et al.
Publicado: (2024)

Non-Asymptotic Analysis of Ensemble Kalman Updates: Effective Dimension and Localization
por: Ghattas, Omar Al, et al.
Publicado: (2022)

Mode-wise Principal Subspace Pursuit and Matrix Spiked Covariance Model
por: Tang, Runshi, et al.
Publicado: (2023)

Probabilistic Analysis of Least Squares, Orthogonal Projection, and QR Factorization Algorithms Subject to Gaussian Noise
por: Lotfi, Ali, et al.
Publicado: (2024)

Regularized Stein Variational Gradient Flow
por: He, Ye, et al.
Publicado: (2022)

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
por: Nazari, Parvin, et al.
Publicado: (2025)

Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
por: Paik, Seunghoon, et al.
Publicado: (2025)

A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
por: Li, Gen, et al.
Publicado: (2024)

Sampling and estimation on manifolds using the Langevin diffusion
por: Bharath, Karthik, et al.
Publicado: (2023)

Characteristic Learning for Provable One Step Generation
por: Ding, Zhao, et al.
Publicado: (2024)