infrastructure
Small Models Translate Network Intent—Until the Wording Moves
Ten sub-10-billion-parameter models reach 0.943 strict F1, but realistic rephrasing weakens invalid-intent rejection.
Summary
Ten sub-10-billion-parameter models reach 0.943 strict F1, but realistic rephrasing weakens invalid-intent rejection.
Across 716 placement intents, the strongest lightweight configurations translated operator requests into service-level objectives with 0.943 strict F1 and rejected as many as 191 of 195 invalid requests. Few-shot reasoning cut unsupported QoS hallucinations to roughly one response in a hundred for the best models, at an energy cost of 0.044 to 0.148 Wh per translation without reasoning. Yet realistic paraphrases reduced invalid-intent rejection in 15 of 16 tested setups, leaving robustness as the central deployment gap.
Why it matters
Ten sub-10-billion-parameter models reach 0.943 strict F1, but realistic rephrasing weakens invalid-intent rejection.
Limits and context
No additional limitation was separately recorded.
Key claims
Ten sub-10-billion-parameter models reach 0.943 strict F1, but realistic rephrasing weakens invalid-intent rejection.
Evidence: source-2026-11-07-004
Sources
- arXiv preprint 2611.07982, original v1arXiv · primary research
Corrections
: Publication note: This November 7 edition was assembled before its scheduled 9:00 AM America/Detroit reveal but is being published late after recovery from a local build interruption. Its original reporting, image-generation times and scheduled publishAt are preserved.