arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.12862cs.CL
收藏

语言模型的认识论:语言模型是否具有整体性知识?

Epistemology of Language Models: Do Language Models Have Holistic Knowledge?

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST))

Minsu Kim, James Thorne

AI总结:

本文从认识论整体主义视角,通过溯因、修正和论证生成三个任务检验大语言模型是否具备整体性知识,发现其仅在溯因任务中避免修正核心知识,整体上未能区分核心与边缘知识。

摘要:

本文从认识论整体主义的视角研究语言模型中的固有知识。本文旨在探讨大语言模型(LLMs)是否表现出与认识论整体主义一致的特征。这些特征表明,核心知识(如一般科学知识)各自发挥着特定作用,作为我们知识体系的基础,并且难以被修正。为了评估这些与整体主义相关的特质,我们创建了一个科学推理数据集,并通过三个任务检验了语言模型的认识论:溯因、修正和论证生成。在溯因任务中,语言模型在解释情境时避免了修正核心知识。然而,在其他任务中,语言模型被揭示出不能区分核心知识与边缘知识,显示出与整体性知识原则的不完全对齐。

英文摘要:

This paper investigates the inherent knowledge in language models from the perspective of epistemological holism. The purpose of this paper is to explore whether LLMs exhibit characteristics consistent with epistemological holism. These characteristics suggest that core knowledge, such as general scientific knowledge, each plays a specific role, serving as the foundation of our knowledge system and being difficult to revise. To assess these traits related to holism, we created a scientific reasoning dataset and examined the epistemology of language models through three tasks: Abduction, Revision, and Argument Generation. In the abduction task, the language models explained situations while avoiding revising the core knowledge. However, in other tasks, the language models were revealed not to distinguish between core and peripheral knowledge, showing an incomplete alignment with holistic knowledge principles.

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。

↑