Metraipolis › archive › dc_7471cd1b3229

Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures — arXiv:2609.00764

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00764
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:37.364Z
SHA-256 of the archived text
3085e69b78ae39c1be5dd8f5d80fe0350b7fb98d361372640db9f3ee86527074
Stable URL of this page
https://metraipolis.com/documento/dc_7471cd1b3229

How to cite

Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures — arXiv:2609.00764 — arXiv (en), https://arxiv.org/abs/2609.00764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7471cd1b3229 (Metraipolis archive dc_7471cd1b3229, sha256 3085e69b78ae39c1be5dd8f5d80fe0350b7fb98d361372640db9f3ee86527074)
BibTeX
@misc{dc7471cd1b3229,
  title = {Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures — arXiv:2609.00764},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00764},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7471cd1b3229; sha256 3085e69b78ae39c1be5dd8f5d80fe0350b7fb98d361372640db9f3ee86527074},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural networks are increasingly employed to identify both well-defined and ambiguous concepts, yet output-level metrics reveal little about how those concepts are represented internally. Our study asks if these networks exhibit \textit{conceptual separation}: if examples of the same concept form coherent representations, and whether related concepts lie closer together in the representation space. We examine this conceptual organisation in Convolutional Neural Networks (CNNs) and Large Language Models (LLMs) through geometric and distributional analysis of their internal activations. In CNNs, familiar ImageNet concepts form coherent and semantically ordered representations, while this coherence weakens for unseen concepts and suffers within-class domain shift. In LLMs, clearly distinct domains remain well separated, related subdomains move closer together, and the distinction between ambiguous topics collapses at both the mean and covariance level. These results suggest that conceptual separation can reveal structure that output accuracy alone cannot, and may serve as a useful diagnostic of how robustly a model represents the concepts it is asked to identify. Code and data available on \href{ this https URL }{GitHub}.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.00764 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.816Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).