arXiv Machine Learning June 10, 2026 By Sophie Zhao

A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations

Read the original on arXiv Machine Learning →

arXiv:2606. 09894v1 Announce Type: new Abstract: Across contemplative, philosophical, and psychological accounts, human consciousness is often described along a similar spectrum, ranging from reactive and self-focused patterns to more integrative and coherent ones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Trajectory Geometry of Transformer Representations Across Layers

arXiv:2606. 09287v1 Announce Type: new Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability.

By Vishal Pandey, Gopal Singh

llms rag safety

arXiv AI

Jun 3

Decomposing how prompting steers behavior

arXiv:2606. 03093v1 Announce Type: new Abstract: Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates, but it remains unclear how instruction changes reshape internal representations to produce behavior.

By Fan L. Cheng, Nikolaus Kriegeskorte

llms multimodal

arXiv Computer Vision

Aug 24

Aristotelian Manifolds: Leveraging Platonic Perceptual Features for Backpropagation Free Rapid Concept Learning

arXiv:2608.20682v1 Announce Type: new Abstract: This paper formalizes and systematically characterizes Aristotelian Manifolds, a generalized structural framework built upon the Platonic Representatio...

By Michael Karnes, Alper Yilmaz

arXiv Computation and Language

Aug 24

Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds

The paper shows that large language models (LLMs) naturally organize their hidden state manifolds into small‑world networks, enabling efficient multi‑hop reasoning. By converting similarity matrices into unweighted graphs, the authors trace connectivity between distant semantic anchors and find a sharp topological phase transition: deep reasoning layers compress conceptual distances into paths bounded by six semantic hops, while early syntactic layers remain fragmented. The framework is applied to zero‑shot hallucination detection in Retrieval‑Augmented Generation, revealing that factual generations preserve a ~3‑hop structure, whereas hallucinations collapse the topology.

By Md. Faiyaz Abdullah Sayeedi

llms rag safety

arXiv Machine Learning

Sep 10

Capsule Lens: Locating and Tracking Concept Geometry in Model Representations

arXiv:2609.05575v1 Announce Type: new Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability,...

By Yiming Tang, Harshvardhan Saini, Samyak Jha, Huaming Chen, Xufeng Duan, Dianbo Liu

nlp reinforcement-learning safety

arXiv AI

Jun 4

A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks

arXiv:2510. 24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities.

By Silin Chen, Yuzhong Chen, Caiwei Wang, Zifan Wang, Junhao Wang, Zifeng Jia, Keith M Kendrick, Tuo Zhang, Lin Zhao, Dezhong Yao, Tianming Liu, Xi Jiang

llms fine-tuning multimodal safety