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 2410.20199cs.AI
收藏

重新思考不确定性:大语言模型时代的批判性综述与分析

Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models

Virginia Tech(弗吉尼亚理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The University of Texas at Dallas(德克萨斯大学达拉斯分校);University of California, Davis(加州大学戴维斯分校)

Mohammad Beigi, Sijia Wang, Ying Shen, Zihao Lin, Adithya Kulkarni, Jianfeng He, Feng Chen, Ming Jin, Jin-Hee Cho, Dawei Zhou, Chang-Tien Lu, Lifu Huang

AI总结:

本文针对大语言模型不确定性估计中概念不清、来源不明的问题,提出系统分类与来源分析框架,梳理相关概念、现有方法局限及未来可靠性研究方向。

摘要:

近年来,大语言模型(LLM)已成为广泛人工智能应用的基础。随着LLM使用范围扩大,精确估计其预测中的不确定性变得至关重要。当前方法往往难以准确识别、测量和处理真正的不确定性,其中许多方法主要集中于估计模型置信度。这一差异在很大程度上源于对不确定性在何处、何时以及如何被注入模型的理解不完整。本文提出了一个综合框架,专门用于识别和理解与LLM独特特征相符的不确定性类型和来源。我们的框架通过系统地分类和定义每一种不确定性,增强了对多样化不确定性图景的理解,从而为开发能够精确量化这些不确定性的针对性方法奠定坚实基础。我们还详细介绍了关键相关概念,并考察了当前方法在关键任务和安全敏感应用中的局限性。论文最后展望了未来方向,旨在提升这些方法在真实场景中的可靠性和实际采用程度。

英文摘要:

In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications. As the use of LLMs expands, precisely estimating the uncertainty in their predictions has become crucial. Current methods often struggle to accurately identify, measure, and address the true uncertainty, with many focusing primarily on estimating model confidence. This discrepancy is largely due to an incomplete understanding of where, when, and how uncertainties are injected into models. This paper introduces a comprehensive framework specifically designed to identify and understand the types and sources of uncertainty, aligned with the unique characteristics of LLMs. Our framework enhances the understanding of the diverse landscape of uncertainties by systematically categorizing and defining each type, establishing a solid foundation for developing targeted methods that can precisely quantify these uncertainties. We also provide a detailed introduction to key related concepts and examine the limitations of current methods in mission-critical and safety-sensitive applications. The paper concludes with a perspective on future directions aimed at enhancing the reliability and practical adoption of these methods in real-world scenarios.

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。

↑