为大模型文本生成的不确定性提供统一分析框架
A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
- 将提示、生成、解释视为关联的自回归过程，构建采样树
- 通过过滤器和目标函数量化不同环节的不确定性
- 揭示现有方法的共性与未被研究的不确定因素
大型语言模型（LLMs）生成文本具有内在不确定性，其来源不仅包括文本生成本身，还涉及输入提示和下游理解。本文提出一个形式化框架，用于综合衡量这些不同层面的不确定性。该框架将提示、生成和解释建模为相互关联的自回归过程，并可整合为单一采样树。通过引入过滤器和目标函数，描述不同不确定性维度在采样树上的表达方式，并展示了如何用这些函数形式化现有不确定性方法。本框架不仅揭示了多种方法之间的形式关联并可归约为共同核心，还指出了尚未充分研究的额外不确定性方面。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。