Epistemology of Language Models: Do Language Models Have Holistic Knowledge?
It addresses the problem of understanding knowledge representation in language models for AI researchers, but the findings are incremental as they reveal limitations without major breakthroughs.
This paper investigates whether language models exhibit holistic knowledge by testing them on scientific reasoning tasks, finding that they avoid revising core knowledge in abduction but fail to distinguish core from peripheral knowledge in other tasks, indicating incomplete alignment with holistic principles.
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.