Skip to content

One mechanism for many mental spaces: a shared router over a value slot in language models

Jul 2026 · arXiv.org · Vol abs/2607.10248 · 2 citations · 22 references
Computer Science

TL;DR

This paper establishes the cross-type generality of belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).

Abstract

Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive). Fauconnier's mental-space theory, by contrast, treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families. Belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).

View source

Similar papers

#natural language process... Preprint Oct 2026

What Is the"Self"of a Large Language Model?

What could the"self"of a large language model be, if it is neither a particular word nor a single privileged layer? We propose a relational account: a functional self is an actor-centered organization of information that distinguishes the model's recorded actions from externally supplied material while content and reas...

Yu-Chen Li, Zong-Qi Fan, Xin-Tong Li et al. · 0 citations
Open access 2026

How Are Large Language Models Fallible

Large Language Models (LLMs) operate within closed neural architectures, isolated from direct physical interaction with the external world. This lack of empirical grounding is a critical epistemic deficiency of empirical theories to explain the referential nature of LLM outputs and their hallucinatory fallibility. To a...

Boris Grozdanoff · 0 citations
Preprint Aug 2026

Walking on the DARKSIDE

The evidence supports an architectural claim: when an LLM forward pass is wrapped in an ontology-mediated auditing, structurally inevitable hallucination can be partially recovered.

A. Gangemi, E. Bottazzi · 1 citation

Language Models Act on Hidden Valence

It is demonstrated that valence-related activation patterns leave hidden traces that predictably govern later choices, even when all visible tokens are identical across conditions, and whether these traces are accompanied by any subjective experience relevant to model welfare remains unclear.

Cameron Berg, Caspar Kaiser · 2 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.