Metraipolis › archive › dc_90dc83ff7906

How Far Can Lightweight LLMs Go in Intent-to-SLO Translation? — arXiv:2611.07982

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07982
License (as archived): CC0-1.0
Archived: 2026-11-06T14:43:21.159Z
SHA-256 of the archived text: 53da0b17d7dcba0c8bace5607aea61ca256a6ca07ba60fc3788e5631c2e60651
Stable URL of this page: https://metraipolis.com/documento/dc_90dc83ff7906

How to cite

How Far Can Lightweight LLMs Go in Intent-to-SLO Translation? — arXiv:2611.07982 — arXiv (en), https://arxiv.org/abs/2611.07982 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90dc83ff7906 (Metraipolis archive dc_90dc83ff7906, sha256 53da0b17d7dcba0c8bace5607aea61ca256a6ca07ba60fc3788e5631c2e60651)

BibTeX

@misc{dc90dc83ff7906,
  title = {How Far Can Lightweight LLMs Go in Intent-to-SLO Translation? — arXiv:2611.07982},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07982},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90dc83ff7906; sha256 53da0b17d7dcba0c8bace5607aea61ca256a6ca07ba60fc3788e5631c2e60651},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07982. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Intent-based networking (IBN) promises QoS provisioning in which the network derives the configuration from operator-stated goals. Its first step, translating a natural-language intent into enforceable service-level objectives (SLOs) grounded in a live snapshot of the network state, increasingly relies on large language models (LLMs). These large models add cost and energy to the management loop and typically require multi-GPU, cloud-hosted infrastructure. Can lightweight open LLMs take over this step dependably? We answer this question with a five-dimensional evaluation of ten LLMs with <10B parameters from five families, under four prompting setups, on 716 placement intents. We evaluate translation performance, intent validation, hallucination, energy impact, and robustness to diverse phrasing. The best configurations translate intents with a strict F1 of 0.943 and reject up to 191 of 195 invalid intents. With few-shot reasoning, the strongest models hallucinate unsupported QoS requirements in only about one response in a hundred, whereas the zero-shot setup struggles. A translated intent costs 0.044-0.148 Wh of GPU energy without reasoning, and added energy cost for reasoning pays off for the weaker models. Furthermore, we show that realistic rephrasing lowers the rejection of invalid intents in 15 of 16 configurations for the best-performing models, leaving robust intent validation as a key open challenge for reliable IBN. Our code and data are available: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.07982 — 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 2026-11-06T14:18:57.598Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).