Metraipolis › archive › dc_50060cb56be3
Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach — arXiv:2610.07093
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07093
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:21.480Z
- SHA-256 of the archived text
335e07261fbf494c8d23523c5dd6ca5330ba640044afe69fc603948f816cdfe9- Stable URL of this page
https://metraipolis.com/documento/dc_50060cb56be3
How to cite
Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach — arXiv:2610.07093 — arXiv (en), https://arxiv.org/abs/2610.07093 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50060cb56be3 (Metraipolis archive dc_50060cb56be3, sha256 335e07261fbf494c8d23523c5dd6ca5330ba640044afe69fc603948f816cdfe9)
BibTeX
@misc{dc50060cb56be3,
title = {Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach — arXiv:2610.07093},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07093},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50060cb56be3; sha256 335e07261fbf494c8d23523c5dd6ca5330ba640044afe69fc603948f816cdfe9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07093. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rapid proliferation of heterogeneous data sources within the Internet of Things (IoT) across domains such as smart cities, energy management, and environmental monitoring necessitates efficient and scalable data standardization methods. Effective classification of smart data models (SDMs) is essential for facilitating interoperability. However, existing approaches are often limited by high resource consumption and lack applicability in edge environments with constrained computational capabilities. Aiming to bridge this gap, the proposed study evaluates the performance of lightweight open-source language models (LMs) to resolve an input data entity against its corresponding best fitting SDM representation under resource-constrained conditions. It systematically benchmarks a diverse array of models, including general purpose (GP), reasoning-specialized (RS), and code-specialized (CS) architectures, across multiple domain-specific datasets. Addressing the current omission of lightweight, resource-efficient solutions in the literature, the investigation provides significant and valuable insights into model selection, task formulation, and deployment strategies that optimize accuracy and efficiency. A complementary experiment also compares the surveyed large language models (LLMs) against two near-zero-cost similarity baselines (Term Frequency-Inverse Document Frequency (TF-IDF) and a lightweight sentence encoder) on the same task, providing a strong reference point for interpreting the practical value of LLM-based classification on edge platforms. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07093 — 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 2026-10-07T11:15:24.477Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).