What question did this study set out to answer?

To explore how metaphorical understanding of large language models impacts perception of their cognitive abilities.

July 18, 2026Communications Psychology0 citationsOpen Access

Understanding large language models demands distinguishing human projection from machine cognition

LLLingyu LiBeijing Academy of Artificial Intelligence YTYan TengShanghai Key Laboratory of Trustworthy Computing YWYue WangUniversity of Stuttgart

Key Points

To explore how metaphorical understanding of large language models impacts perception of their cognitive abilities.
Analyzed existing metaphors used to understand LLMs across various domains.
Proposed a framework called machine experientialism for interpreting LLMs' functioning.
Identified the recursive loop of anthropomorphism affecting LLM understanding.
Established that LLMs develop a distinct logic from their training data rather than mirroring human cognition.

Abstract

Abstract Current efforts to understand Large Language Models (LLMs) are largely metaphorical. Researchers map LLMs onto familiar domains, from physics and neuroscience to psychology and sociology, each illuminating specific facets while obscuring others. We chart these metaphors across mechanistic, behavioral, and interactive scales and delineate their explanatory boundaries. Crucially, this metaphorical projection creates a recursive loop of anthropomorphism, fueling the “genuine understanding” versus “pattern matching” impasse. As an alternative approach, we propose machine experientialism, positing that LLMs build their own form of understanding from training corpora. The priority shifts from cataloging LLMs’ human-like traits to uncovering their distinct logic that emerges from this text-based world.

Ask AI

Helpful

Bookmark

View Full Paper