arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26363cs.LGcs.CL
收藏

基于大语言模型文本生成的不确定性分析形式框架

A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models

University of Passau(帕绍大学)

Steffen Herbold, Florian Lemmerich

AI总结:

本文提出形式框架以测量文本生成中不确定性,考虑提示、生成和解释的相互关联过程,并展示如何通过过滤器和目标函数表达不确定性,揭示现有方法的关联性及未研究的不确定性方面。

摘要:

使用大语言模型(LLMs)生成文本本质上具有不确定性,其来源不仅包括文本生成本身,还包括提示和下游解释。本文提供了一个正式框架来测量这种不确定性,将提示、生成和解释建模为相互关联的自回归过程,并将其结合为单一的采样树。我们引入过滤器和目标函数,描述如何在采样树上表达不同不确定性的方面,并展示如何通过这些函数表达现有不确定性方法。通过该框架,我们不仅展示了不同方法如何正式相关并可归约为共同核心,还指出了尚未研究的不确定性方面。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑