← Back to all news
arXiv AI By Jaee Ponde, Roshni Agarwal, Subhashis Banerjee

Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures

Read the original on arXiv AI →

The paper investigates whether neural networks exhibit conceptual separation, meaning that examples of the same concept cluster together and related concepts are closer in representation space. Using geometric and distributional analyses, the authors find that Convolutional Neural Networks (CNNs) produce coherent, semantically ordered representations for familiar ImageNet concepts, but this coherence weakens for unseen concepts and under domain shift. Large Language Models (LLMs) keep distinct domains well separated, bring related subdomains closer, yet lose distinction between ambiguous topics at both mean and covariance levels.

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 AI.

Related stories

arXiv Machine Learning
Oct 3

Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models

The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.

By Tido Specht, Elias Benedict Krey, Nils Neukirch, Nils Strodthoff
llmscomputer-visionreinforcement-learningfine-tuningsafety
More like this →
arXiv Computer Vision
Oct 27

Do vision models know that three is three?

arXiv:2610.35857v1 Announce Type: new Abstract: Do vision models encode the transition $2{\to}3$ the same way whether it appears in handwritten digits or in hand gestures, and do they "understand" th...

By Ankit Sonthalia, Arnas Uselis, Seong Joon Oh
llmsrag
More like this →
arXiv AI
Oct 16

ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on

The paper introduces ICON decomposition, a method for auditing neural networks by decomposing the variance of intermediate representations into contributions from Independent Canonical Concepts (ICON). Unlike traditional decodability metrics, ICON isolates each concept’s influence while conditioning on all other concepts and the outcome, providing a clearer view of which concepts truly drive predictions. Experiments on simulated data and real-world skin‑cancer and neuroimaging tasks show ICON outperforms seven baseline methods and successfully distinguishes genuine shortcuts from merely correlated features.

By Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter
More like this →