Guardado en:
Detalles Bibliográficos
Autores principales: Herbold, Steffen, Lemmerich, Florian
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.26363
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911548172140544
author Herbold, Steffen
Lemmerich, Florian
author_facet Herbold, Steffen
Lemmerich, Florian
contents The generation of texts using Large Language Models (LLMs) is inherently uncertain, with sources of uncertainty being not only the generation of texts, but also the prompt used and the downstream interpretation. Within this work, we provide a formal framework for the measurement of uncertainty that takes these different aspects into account. Our framework models prompting, generation, and interpretation as interconnected autoregressive processes that can be combined into a single sampling tree. We introduce filters and objective functions to describe how different aspects of uncertainty can be expressed over the sampling tree and demonstrate how to express existing approaches towards uncertainty through these functions. With our framework we show not only how different methods are formally related and can be reduced to a common core, but also point out additional aspects of uncertainty that have not yet been studied.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26363
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
Herbold, Steffen
Lemmerich, Florian
Machine Learning
Computation and Language
The generation of texts using Large Language Models (LLMs) is inherently uncertain, with sources of uncertainty being not only the generation of texts, but also the prompt used and the downstream interpretation. Within this work, we provide a formal framework for the measurement of uncertainty that takes these different aspects into account. Our framework models prompting, generation, and interpretation as interconnected autoregressive processes that can be combined into a single sampling tree. We introduce filters and objective functions to describe how different aspects of uncertainty can be expressed over the sampling tree and demonstrate how to express existing approaches towards uncertainty through these functions. With our framework we show not only how different methods are formally related and can be reduced to a common core, but also point out additional aspects of uncertainty that have not yet been studied.
title A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2603.26363