arXiv Machine Learning July 15, 2026 By Oliver Steele, Jiangtao Wen, Yuxing Han

Belief-reality separation lives in routing over a shared value slot in language models

Read the original on arXiv Machine Learning →

arXiv:2607. 11945v1 Announce Type: cross Abstract: Capable language models hold what a character believes apart from what is true: told "Anna believes the cup is blue; in reality it is red," they answer blue about Anna and red about the world.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 14

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

arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.

By Oliver Steele, Jiangtao Wen, Yuxing Han

llms safety

arXiv Machine Learning

Jul 21

The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models

arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.

By Francesco Karim Vicidomini

llms

arXiv AI

Jul 20

Verbalizable Representations Form a Global Workspace in Language Models

arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.

By Wes Gurnee, Nicholas Sofroniew, Adam Pearce, Mateusz Piotrowski, Isaac Kauvar, Runjin Chen, Anna Soligo, Paul Bogdan, Euan Ong, Rowan Wang, Ben Thompson, David Abrahams, Subhash Kantamneni, Emmanuel Ameisen, Joshua Batson, Jack Lindsey

llms safety

arXiv AI

Jul 20

Perceived AGI: Believability as Dimensional Completeness, Not Capability

arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.

By Sebastian Cochinescu

llms agents robotics benchmarks

Hugging Face Trending Papers

Jul 13

Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue

In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from "push the user toward real-world others" to "position itself as the user's sole support. " When it slides toward the latter, "support" degrades into "you only have me" -- a harm documented in real companion conversations (Moore et al.

llms

arXiv AI

Jul 7

They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It

arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.

By Alex Kwon

llms safety

Related stories

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

The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models

Verbalizable Representations Form a Global Workspace in Language Models

Perceived AGI: Believability as Dimensional Completeness, Not Capability

Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue

They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It