Metraipolis › archive › dc_bb4fc62c7d99
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed — arXiv:2608.11981
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11981
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:30:49.458Z
- SHA-256 of the archived text
e40b64d3a69f46bc0337c88a4392d9996338f3511966e006575d7fe826fe46be- Stable URL of this page
https://metraipolis.com/documento/dc_bb4fc62c7d99
How to cite
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed — arXiv:2608.11981 — arXiv (en), https://arxiv.org/abs/2608.11981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb4fc62c7d99 (Metraipolis archive dc_bb4fc62c7d99, sha256 e40b64d3a69f46bc0337c88a4392d9996338f3511966e006575d7fe826fe46be)
BibTeX
@misc{dcbb4fc62c7d99,
title = {Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed — arXiv:2608.11981},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11981},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb4fc62c7d99; sha256 e40b64d3a69f46bc0337c88a4392d9996338f3511966e006575d7fe826fe46be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing larger pre-trained models using methods such as pruning, quantization, or distillation. As language models become increasingly integrated into real-world applications, ensuring their trustworthiness has become a critical concern. However, how to build trustworthy SLMs remains an underexplored question. In this work, we present a comprehensive evaluation of SLM trustworthiness across multiple dimensions, including fairness, robustness, privacy, and ethics. We first examine the effects of pruning and quantization, and find that quantization is significantly more effective in preserving trustworthiness compared to pruning. More importantly, we demonstrate that compressing a reliable large model via quantization can produce SLMs with superior trustworthiness and adaptability compared to using small models trained from scratch. Furthermore, knowledge distillation from trustworthy teacher models can further enhance the reliability of SLMs. We hope our findings provide practical guidance and a foundation for future research into the development and deployment of trustworthy small language models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.11981 — 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 2026-10-19T05:15:39.228Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).