Metraipolis › archive › dc_a7e1ce8df604
SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension — arXiv:2608.07254
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07254
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:51:37.564Z
- SHA-256 of the archived text
a30b79502e44a4ade0e7757811c18fd95f1af52f60d60db0db38965988e30386- Stable URL of this page
https://metraipolis.com/documento/dc_a7e1ce8df604
How to cite
SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension — arXiv:2608.07254 — arXiv (en), https://arxiv.org/abs/2608.07254 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7e1ce8df604 (Metraipolis archive dc_a7e1ce8df604, sha256 a30b79502e44a4ade0e7757811c18fd95f1af52f60d60db0db38965988e30386)
BibTeX
@misc{dca7e1ce8df604,
title = {SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension — arXiv:2608.07254},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07254},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7e1ce8df604; sha256 a30b79502e44a4ade0e7757811c18fd95f1af52f60d60db0db38965988e30386},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07254. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disciplines and research topics but often fail to capture the fine-grained conceptual structure of contemporary science. Author keywords offer greater specificity, but their fragmentation, redundancy, and terminological variability limit their use as stable units of knowledge organization. We introduce SCALE (Scientific Concept Aggregation via LLMs and Embeddings), a framework that extends the OpenAlex taxonomy with a new level of scientific Concepts below Topics. Rather than treating keywords as isolated descriptors, SCALE organizes semantically related terms into coherent and interpretable conceptual units and integrates them within the existing disciplinary hierarchy. The framework combines scientific text embeddings, large language models, and graph-based community detection to construct this additional layer at scale. The resulting taxonomy enables scientific literature to be read through an intermediate conceptual level between broad research topics and individual documents. This perspective provides a more detailed representation of how scientific knowledge is structured, specialized, and connected across disciplines. By transforming heterogeneous author terminology into reusable hierarchical units, SCALE offers a foundation for fine-grained scholarly classification, scientometric analysis, research monitoring, and future ontology development. Tema degli esploratori: ricerca e scienza aperta (retro-catalogo arXiv: annunci del 2026-08-10 in cs.DL). Categorie arXiv: Digital Libraries (cs.DL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.07254 — 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 2026-10-19T09:50:04.569Z dalla pagina https://arxiv.org/catchup/cs.DL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).