Upload README.md with huggingface_hub

README.md

@@ -88,6 +88,20 @@ Comparing two-stage pipeline (bi-encoder + reranker) vs bi-encoder alone:
 
 The reranker provides significant gains on complex, multi-part queries typical of board exam questions.
 
+### Published Benchmark Results
+
+From [Matulich & Mason, 2026](https://huggingface.co/matulichpt/radlit-biencoder):
+
+| Benchmark | RadLIT Result | Key Finding |
+|-----------|---------------|-------------|
+| NFCorpus nDCG@10 | 0.268 | **17.9x improvement** over RadBERT bi-encoder (0.015) |
+| VQA-RAD MRR | 0.972 | Near-perfect retrieval on radiology Q&A |
+| RadLIT-9 Thoracic | 0.736 nDCG@10 | **Best-in-class** (beat BGE-large, ColBERTv2) |
+| RadLIT-9 Pediatric | 0.625 nDCG@10 | **Best-in-class** (beat BGE-large, ColBERTv2) |
+| Zebra Test | 92% found rate | 2.1x improvement on rare conditions vs ColBERTv2 |
+
+**Vocabulary Alignment Hypothesis**: Domain training provides measurable advantage when queries use radiology-specific terminology that aligns with the training domain.
+
 ## Quick Start
 
 ### Installation
@@ -359,13 +373,13 @@ reranker = CrossEncoder(
 If you use RadLITE in your work, please cite:
 
 ```bibtex
-@software{radlite_2026,
-    title = {RadLITE: Calibrated Multi-Stage Retrieval for Radiology Education},
-    author = {Grai Team},
+@article{matulich2026radlit,
+    title = {Late Interaction Retrieval Unlocks Domain Knowledge in Radiology Language Models},
+    author = {Matulich, Patrick and Mason, Dan},
     year = {2026},
-    month = {January},
-    url = {https://huggingface.co/matulichpt/radlit-crossencoder},
-    note = {MRR 0.829 on RadLIT-9 benchmark}
+    journal = {Radiology: Artificial Intelligence},
+    note = {17.9x improvement over RadBERT; best-in-class on Thoracic/Pediatric subspecialties},
+    url = {https://huggingface.co/matulichpt/radlit-biencoder}
 }
 ```