Update README.md

README.md

@@ -90,15 +90,7 @@ We evaluated MultiClinicalBERT on **8 clinical NLP tasks across 4 languages**:
 - Japanese: IFMIR Incident Type, IFMIR NER
 - Spanish: EHR De-identification, PPTS
 
-### Retrieval Augmented Generation (RAG)
-
-![rag_results_figure](https://cdn-uploads.huggingface.co/production/uploads/690e53164670480464c0d207/I-r8vU_CVlSVCrLiyezft.png)
-
-We further evaluated whether MultiClinicalBERT could enhance downstream clinical classification by retrieving external, unlabeled knowledge from language-matched Wikipedia corpora.
-
-Across four clinical classification benchmarks and three Qwen3.5 model sizes (i.e., 2B, 4B, 9B), **MultiClinicalBERT achieved the highest overall average performance among the seven retrieval approaches.**
-
-### Key Results
+#### Key Results
 - Consistently outperforms Modern multilingual BERT (mmBERT)
 - Matches or exceeds strong language-specific models
 - Largest gains observed in low-resource settings
@@ -110,6 +102,15 @@ Example:
 - IFMIR NER: **86.21 F1**
 - EHR De-identification: **88.64 F1**
 
+### Retrieval Augmented Generation (RAG)
+
+![rag_results_figure](https://cdn-uploads.huggingface.co/production/uploads/690e53164670480464c0d207/I-r8vU_CVlSVCrLiyezft.png)
+
+We further evaluated whether MultiClinicalBERT could enhance downstream clinical classification by retrieving external, unlabeled knowledge from language-matched Wikipedia corpora.
+
+Across four clinical classification benchmarks and three Qwen3.5 model sizes (i.e., 2B, 4B, 9B), **MultiClinicalBERT achieved the highest overall average performance among the seven retrieval approaches.**
+
+
 
 ## Key Contributions