CLAIJun 19, 2025

Can structural correspondences ground real world representational content in Large Language Models?

arXiv:2506.16370v14 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis

This addresses a foundational philosophical and practical issue for AI researchers and theorists about the limits of LLM capabilities, but it is incremental as it builds on existing structural-correspondence theories.

The paper tackles the problem of whether Large Language Models (LLMs) can represent real-world entities, given their text-only training, and argues that structural correspondences alone are insufficient for grounding representation, requiring appropriate task exploitation instead.

Large Language Models (LLMs) such as GPT-4 produce compelling responses to a wide range of prompts. But their representational capacities are uncertain. Many LLMs have no direct contact with extra-linguistic reality: their inputs, outputs and training data consist solely of text, raising the questions (1) can LLMs represent anything and (2) if so, what? In this paper, I explore what it would take to answer these questions according to a structural-correspondence based account of representation, and make an initial survey of this evidence. I argue that the mere existence of structural correspondences between LLMs and worldly entities is insufficient to ground representation of those entities. However, if these structural correspondences play an appropriate role - they are exploited in a way that explains successful task performance - then they could ground real world contents. This requires overcoming a challenge: the text-boundedness of LLMs appears, on the face of it, to prevent them engaging in the right sorts of tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes