paper-with-me

Papers

On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs

2025-10-06 · Lucie Kunitomo-Jacquin, Edison Marrese-Taylor, Ken Fukuda arxiv

Quantifying uncertainty in large language models (LLMs) is important for safety-critical applications because it helps spot incorrect answers, known as hallucinations. One major trend of uncertainty quantification methods is based on estimating the entropy of the distribution of the LLM's potential output sequences. This estimation is based on a set of output sequences and associated probabilities obtained by querying the LLM several times. In this paper, we advocate and experimentally show that the probability of unobserved sequences plays a crucial role, and we recommend future research to integrate it to enhance such LLM uncertainty quantification methods.

📄 PDF Abstract BibTeX arXiv:2510.04439

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Instrumental and Proximal Causal Inference with Gaussian Processes

2026-03-02 · Yuqi Zhang, Krikamol Muandet, Dino Sejdinovic, Edwin Fong 외 arxiv

Instrumental variable (IV) and proximal causal learning (Proxy) methods are central frameworks for causal inference in the presence of unobserved confounding. Despite substantial methodological advances, existing approac…

Gaussian ProcessesCausal Inference

Neural density estimation and uncertainty quantification for laser induced breakdown spectroscopy spectra

2021-08-17 · Katiana Kontolati, Natalie Klein, Nishant Panda, Diane Oyen

Constructing probability densities for inference in high-dimensional spectral data is often intractable. In this work, we use normalizing flows on structured spectral latent spaces to estimate such densities, enabling do…

Density EstimationOut-of-Distribution DetectionUncertainty Quantification

Neural Visibility Field for Uncertainty-Driven Active Mapping

2024-06-11 · CVPR 2024 1 · Shangjie Xue, Jesse Dill, Pranay Mathur, Frank Dellaert 외

This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views …

NeRFPositionUncertainty Quantification

SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process

2023-10-25 · Zichong Li, Yanbo Xu, Simiao Zuo, Haoming Jiang 외

Transformer Hawkes process models have shown to be successful in modeling event sequence data. However, most of the existing training methods rely on maximizing the likelihood of event sequences, which involves calculati…

PredictionType predictionUncertainty Quantification

Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles

2025-04-17 · Tirtha Vinchurkar, Kareem Abdelmaqsoud, John R. Kitchin

Machine-learned potentials (MLPs) have revolutionized materials discovery by providing accurate and efficient predictions of molecular and material properties. Graph Neural Networks (GNNs) have emerged as a state-of-the-…

Active LearningUncertainty Quantification