Upload README.md with huggingface_hub

README.md

@@ -32,9 +32,9 @@ model-index:
     - type: mrr
       value: 0.829
       name: MRR (with bi-encoder)
-    - type: mrr_improvement
-      value: 0.303
-      name: MRR Improvement on ACR Core Exam (+30.3%)
+    - type: mrr
+      value: 0.533
+      name: MRR on ABR Core Exam (Chest)
 ---
 
 # RadLITE-Reranker
@@ -43,7 +43,7 @@ model-index:
 
 A domain-specialized cross-encoder for reranking radiology search results. This model takes a query-document pair and predicts a relevance score, providing more accurate ranking than bi-encoder similarity alone.
 
-> **Recommended:** Use this reranker together with [RadLITE-Encoder](https://huggingface.co/matulichpt/radlit-biencoder) in a two-stage pipeline for optimal performance. The bi-encoder handles fast retrieval over large corpora, then this cross-encoder reranks the top candidates for precision. This combination achieves **MRR 0.829** on radiology benchmarks (+30% on board exam questions).
+> **Recommended:** Use this reranker together with [RadLITE-Encoder](https://huggingface.co/matulichpt/radlit-biencoder) in a two-stage pipeline for optimal performance. The bi-encoder handles fast retrieval over large corpora, then this cross-encoder reranks the top candidates for precision. This combination achieves **MRR 0.829** on radiology retrieval benchmarks.
 
 ## Model Description
 
@@ -77,14 +77,16 @@ Bi-encoders (like RadLITE-Encoder) are fast but encode query and document indepe
 | Bi-Encoder only | 0.78 | baseline |
 | **Bi-Encoder + Reranker** | **0.829** | **+6.3%** |
 
-### ACR Core Exam (Board-Style Questions)
+### ABR Core Exam (Board-Style Questions)
+
+Comparing two-stage pipeline (bi-encoder + reranker) vs bi-encoder alone:
 
-| Dataset | With Reranker | Without | Improvement |
-|---------|---------------|---------|-------------|
-| Core Exam Chest | 0.533 | 0.409 | **+30.3%** |
-| Core Exam Combined | 0.466 | 0.381 | **+22.5%** |
+| Dataset | Two-Stage MRR | Bi-Encoder Only | Improvement |
+|---------|---------------|-----------------|-------------|
+| Core Exam Chest | 0.533 | 0.409 | +30.3% |
+| Core Exam Combined | 0.466 | 0.381 | +22.5% |
 
-The reranker is especially valuable for complex, multi-part queries typical of board exam questions.
+The reranker provides significant gains on complex, multi-part queries typical of board exam questions.
 
 ## Quick Start
 
@@ -363,7 +365,7 @@ If you use RadLITE in your work, please cite:
     year = {2026},
     month = {January},
     url = {https://huggingface.co/matulichpt/radlit-crossencoder},
-    note = {+30% MRR improvement on ACR Core Exam questions}
+    note = {MRR 0.829 on RadLIT-9 benchmark}
 }
 ```