Metraipolis › archive › dc_462d0424bb03
SALUTE: Benchmarking and Adapting LLMs for the Defense Domain — arXiv:2609.15022
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15022
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:15:48.974Z
- SHA-256 of the archived text
f74c51d3e9699f869f0380fb8a8e8a32b4e47d3538d0a57f44a961e274261242- Stable URL of this page
https://metraipolis.com/documento/dc_462d0424bb03
How to cite
SALUTE: Benchmarking and Adapting LLMs for the Defense Domain — arXiv:2609.15022 — arXiv (en), https://arxiv.org/abs/2609.15022 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_462d0424bb03 (Metraipolis archive dc_462d0424bb03, sha256 f74c51d3e9699f869f0380fb8a8e8a32b4e47d3538d0a57f44a961e274261242)
BibTeX
@misc{dc462d0424bb03,
title = {SALUTE: Benchmarking and Adapting LLMs for the Defense Domain — arXiv:2609.15022},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15022},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_462d0424bb03; sha256 f74c51d3e9699f869f0380fb8a8e8a32b4e47d3538d0a57f44a961e274261242},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15022. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Defense is a knowledge-intensive domain that requires precise understanding of specialized terminology, doctrinal concepts, operational procedures, and evolving military events. Although recent work has explored language technologies for military applications, existing efforts remain fragmented: they are often task-specific, rely on limited adaptation pipelines, or lack comprehensive defense-domain evaluation. In this paper, we present SALUTE, an end-to-end framework for benchmarking and adapting LLMs for the defense domain. SALUTE integrates Salute-Corpus, a curated corpus from open-access U.S. military doctrine and government documents; Salute-Conv, a grounded instruction dataset from doctrinal sources and decade-long defense news; Salute-Pref, a defense-aware preference dataset; and Salute-Bench, a rigorously filtered benchmark for evaluating defense-domain understanding and reasoning over doctrine and defense news. Based on these resources, we train Salute-LLM through multi-stage post-training with continual pretraining, supervised fine-tuning, and preference alignment. Extensive experiments show that Salute-LLM achieves strong defense-domain performance while retaining competitive general capabilities, demonstrating the effectiveness of SALUTE as an end-to-end framework for defense-domain LLM adaptation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.15022 — 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 2026-10-15T22:51:09.927Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).