Hugging Face Blog·· 3 d ago
LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B
LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B
AI summary
LLMs rely on their context to generate the next set of tokens. To address this, we developed LLMON (LLM Object Notation, pronounced “lemon”), an LLM-native markup language for explicitly communicating structure and semantics to the models.
Selection record
Threshold 60Official, first-handFirst 71Second 62
AdmittedSum of both 133 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：发布LLM原生标记语言及模型，属AI技术
- Why it was chosen
- Sets out why LLMON was designed and compares it against prompt-injection benchmarks, showing how structured context affects the robustness of small models.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co