The Vector Grounding Problem

Journal article

Large language models (LLMs) produce seemingly meaningful outputs, yet they are trained on text alone without direct interaction with the world. This leads to a modern variant of the classical symbol grounding problem in AI: can LLMs’ internal states and outputs be about extra-linguistic reality, independently of the meaning human interpreters project onto them? We argue that they can. We first distinguish referential grounding—the connection between a representation and its worldly referent—from other forms of grounding and argue it is the only kind essential to solving the problem. We contend that referential grounding is achieved when a system’s internal states satisfy two conditions derived from teleosemantic theories of representation: (1) they stand in appropriate causal-informational relations to the world, and (2) they have a history of selection that has endowed them with the function of carrying this information. We argue that LLMs can meet both conditions, even without multimodality or embodiment.

Authors: Mollo, DC; Millière, R

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Universitatsbibliothek der Ruhr-Universitat Bochum
• Journal: Philosophy and the Mind Sciences
• Volume: 7
• Issue: 1
• Pages: 1-28
• Publication date: 2026-02-27
• DOI: 10.33735/phimisci.2026.12307
• EISSN: 2699-0369
• ISSN: 2699-0369
• Language: English
• Keywords: Ground; Function (biology); Symbol (formal); Connection (principal bundle); Selection (genetic algorithm); Interpreter; Meaning (existential); Representation (politics)