Metraipolis › archive › dc_246b97a369ea

Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization — arXiv:2609.04486

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04486
License (as archived)
CC0-1.0
Archived
2026-10-16T22:35:54.647Z
SHA-256 of the archived text
01f775da9adef0e286a79c4b0be55fc113b9c269765ecce50a23a47bd0112571
Stable URL of this page
https://metraipolis.com/documento/dc_246b97a369ea

How to cite

Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization — arXiv:2609.04486 — arXiv (en), https://arxiv.org/abs/2609.04486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_246b97a369ea (Metraipolis archive dc_246b97a369ea, sha256 01f775da9adef0e286a79c4b0be55fc113b9c269765ecce50a23a47bd0112571)
BibTeX
@misc{dc246b97a369ea,
  title = {Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization — arXiv:2609.04486},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04486},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_246b97a369ea; sha256 01f775da9adef0e286a79c4b0be55fc113b9c269765ecce50a23a47bd0112571},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Intent-based networking realization starts by translating high-level intents into low-level network configurations. Recent approaches have shifted toward LLM-based translation. Despite promising results, most studies focus on translation accuracy and overlook risks associated with deploying the resulting configurations. In this work, we investigate the pre-deployment translation risk of LLM-generated configurations by analyzing the model's uncertainty. We propose to use two uncertainty signals, namely sampling-based predictive uncertainty for translation-risk ranking and token-level entropy for ambiguity-source localization. We evaluate these signals on an ambiguity-controlled test set across different context types and sampling budgets, using a Llama-3.1-8B-Instruct model fine-tuned for intent translation on a vendor-specific switch platform (Juniper EX3300). The results demonstrate that predictive uncertainty provides a useful signal for ranking translations by risk across context types and sampling budgets, albeit with substantial miscalibration under less informative contexts. Moreover, we show that parameter-token entropy correlates with parameter-sourced ambiguity and keyword-token entropy correlates with description-sourced ambiguity. These results indicate the potential of using uncertainty signals in an LLM-generated configuration deployment pipeline, where predictive uncertainty can support selective deployment, while token-level entropy can identify sources of ambiguity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CL).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.04486 — 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 2026-10-16T22:21:16.317Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).