Metraipolis › archive › dc_a0cd209807b8
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding — arXiv:2608.07353
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07353
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:47:01.528Z
- SHA-256 of the archived text
cf69f2b6de399c8c85c97ca47c9488712c727e8785a12583c4670c0718212d9b- Stable URL of this page
https://metraipolis.com/documento/dc_a0cd209807b8
How to cite
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding — arXiv:2608.07353 — arXiv (en), https://arxiv.org/abs/2608.07353 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0cd209807b8 (Metraipolis archive dc_a0cd209807b8, sha256 cf69f2b6de399c8c85c97ca47c9488712c727e8785a12583c4670c0718212d9b)
BibTeX
@misc{dca0cd209807b8,
title = {Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding — arXiv:2608.07353},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07353},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0cd209807b8; sha256 cf69f2b6de399c8c85c97ca47c9488712c727e8785a12583c4670c0718212d9b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07353. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding concepts is fundamental to generalization. Despite their impressive performance on a wide range of tasks, Large Language Models (LLMs) still struggle with genuine concept understanding. Prior work has evaluated conceptual understanding in LLMs using natural-language benchmarks or narrowly scoped synthetic tasks, but these settings often conflate multiple skills or lack precise control over the underlying concepts and their properties. To support controlled probing of concepts in LLMs, we design tests on their core properties: abstraction, compositionality, and groundness. We set up a concept-centric benchmark, targeting spatial concepts such as direction, distance, topology, and their compositions, and use question answering tasks serving as a proxy. We conduct extensive experiments across multiple LLM architectures and training regimes to analyze how model scale and design impact conceptual understanding. The results reveal clear limitations in current LLMs and provide insights into the factors shaping their ability to acquire and compose structured concepts. Our findings shed light on how concept-based LLMs can be redesigned for improved information access and knowledge management. The code will be available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.07353 — 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 2026-10-19T09:46:37.246Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).