Language Without Propositions

Why Large Language Models Hallucinate

Bibliographic Data

ID22133994
AuthorsJakub Mácha (0000-0001-6394-5173, Masaryk University, corresponding author)
Year2026
Volume11
Issue2
Pages42
Publication date2026-03-19
Open AccessYes
TypeARTICLE
VenuePhilosophies (JOURNAL)
Journal identifiersISSN: 2409-9287 • E-ISSN: 2409-9287
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/philosophies11020042
OpenAlexW7139015829
LanguageEN
References cited30

This paper defends the thesis that LLM hallucinations are best explained as a truth representation problem: Current models lack an internal representation of propositions as truth-bearers, so truth and falsity cannot constrain generation in the way factual discourse requires. It begins by surveying leading explanations—computational limits on self-verification, deficiencies in training data as truth sources, and architectural factors—and argues that they converge on the same underlying representational deficit. Next, it reconstructs the philosophical background of current LLM design, showing how optimization for fluent continuation aligns with coherence-style evaluation and with broadly structuralist, relational semantics, before turning to David Chalmers’s recent attempt to secure propositional interpretability by drawing on Davidson/Lewis-style radical interpretation and by locating propositional content in “middle-layer” structures; it argues that this approach downplays the ubiquity of hallucination and inherits instability from post-training edits. Finally, the paper offers a positive proposal: Atomic propositions should be represented in the basic vector layer, reviving a logical atomist program as a principled route to reducing hallucination

Falsity · Hallucinating · Interpretability · Logical form · Mental representation · Philosophy of language · Venn diagram · Embodied and Extended Cognition · Philosophy and History of Science · Philosophy and Theoretical Science

Tools

Open DOIOpen Access