review

Signed-off-by: bitliu <[email protected]>

Author: Xunzhuo

_posts/2025-12-12-halugate.md

@@ -93,7 +93,7 @@ Running token-level detection on creative writing or code review is wasteful—a
 
 **Why pre-classification matters**: Token-level detection scales linearly with context length. For a 4K token RAG context, detection takes ~125ms; for 16K tokens, ~365ms. In production workloads where ~35% of queries are non-factual, pre-classification achieves a **72.2% efficiency gain**—skipping expensive detection entirely for creative, coding, and opinion queries.
 
-**HaluGate Sentinel** is a ModernBERT-based classifier that answers one question: *Does this prompt warrant factual verification?*
+[HaluGate Sentinel](https://huggingface.co/llm-semantic-router/halugate-sentinel) is a ModernBERT-based classifier that answers one question: *Does this prompt warrant factual verification?*
 
 ![](/assets/figures/semantic-router/halugate-2.png)