arXiv cs.CL· Sabbir Ahmed, Hazem Abbas, Salimur Choudhury·· 11 小时前AI 评分31
轻量级 LLM 在意图到 SLO 翻译中能走多远？
How Far Can Lightweight LLMs Go in Intent-to-SLO Translation?
AI 导读
一项针对 10 个参数量小于 10B 的轻量级开源 LLM 的评估显示，最佳配置在 716 条放置意图上实现 0.943 的严格 F1，并能拒绝 195 条无效意图中的 191 条。
正文 · 原文
Abstract: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.
| Comments: | Under review at ICC 2027. Source code and data: this https URL. (6 pages. 7 figures, 3 tables) |
| Subjects: | Networking and Internet Architecture (cs.NI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.07982 [cs.NI] |
| (or arXiv:2611.07982v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07982 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sabbir Ahmed [view email]
[v1]
Thu, 5 Nov 2026 13:12:30 UTC (271 KB)
来源：arXiv cs.CL · arxiv.org