Update README.md

README.md

@@ -1,5 +1,7 @@
 # BioHiCL-base: Hierarchical Multi-Label Contrastive Biomedical Retriever
 
+## Model Card
+
 ## 🔍 Overview
 BioHiCL-base is a biomedical dense retriever trained with hierarchical MeSH supervision to capture fine-grained semantic relationships between biomedical texts.
 
@@ -12,26 +14,38 @@ Unlike traditional dense retrievers trained with binary relevance signals, BioHi
 - **Multi-label similarity learning**: Captures graded semantic overlap beyond binary relevance  
 - **Contrastive + regression training**: Aligns embedding similarity with label similarity  
 - **Efficient**: ~0.1B parameters, suitable for deployment on a single GPU  
+- **Domain-adapted retriever**: Fine-tuned from a strong general-purpose bi-encoder  
 
 ---
 
 ## 🧠 Model Details
 - **Model type**: Bi-encoder (dense retriever)  
-- **Backbone**: `BAAI/bge-base-en-v1.5`  
+- **Backbone**: BAAI/bge-base-en-v1.5  
 - **Parameters**: ~0.1B  
 - **Fine-tuning**: LoRA (merged into base model)  
 - **Max input length**: 8192 tokens  
+- **Training data**: Biomedical abstracts annotated with MeSH labels (e.g., BioASQ-derived corpora)  
+
+---
+
+## ⚙️ Intended Use
+This model is intended for biomedical information retrieval tasks such as:
+- Scientific literature search (e.g., PubMed-style retrieval)
+- Biomedical document ranking
+- Query–abstract semantic matching
+- Benchmark evaluation on BEIR biomedical subsets
 
 ---
 
 ## ⚙️ How It Works
 BioHiCL aligns:
-- **Embedding similarity (SimE)**: cosine similarity between embeddings  
-- **Label similarity (SimL)**: cosine similarity over weighted MeSH label vectors  
+
+- Embedding similarity (SimE): cosine similarity between document embeddings  
+- Label similarity (SimL): cosine similarity over weighted MeSH multi-label vectors  
 
 ### Training Objective
-- Mean Squared Error (MSE) loss to align SimE with SimL  
-- Hierarchical contrastive loss to separate unrelated documents and prevent embedding collapse  
+- Mean Squared Error (MSE): aligns SimE with SimL  
+- Hierarchical contrastive loss: separates unrelated documents while preserving ontology structure  
 
 ---
 
@@ -39,32 +53,40 @@ BioHiCL aligns:
 
 If you use this model, please cite:
 
-bibtex @article{lan2026biohicl, title={BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels}, author={Lan, Mengfei, Zheng, Lecheng, and Kilicoglu, Halil}, journal={ACL 2026}, year={2026} }
+@article{lan2026biohicl,
+  title={BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels},
+  author={Lan, Mengfei and Zheng, Lecheng and Kilicoglu, Halil},
+  booktitle={ACL 2026},
+  year={2026}
+}
 
+---
 
-## 🚀 Usage — Evaluation on BEIR Benchmark
+## 🚀 Usage (BEIR Evaluation)
 
 ```python
 from beir import util
 from beir.datasets.data_loader import GenericDataLoader
-from beir.retrieval.models import SentenceBERT
+from sentence_transformers import SentenceTransformer
 from beir.retrieval.search.dense import DenseRetrievalExactSearch
 from beir.retrieval.evaluation import EvaluateRetrieval
 
+# Dataset
 dataset = "scifact"
 url = "https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scifact.zip"
 
 data_path = util.download_and_unzip(url, "datasets")
 corpus, queries, qrels = GenericDataLoader(data_path).load(split="test")
 
+# Model
 model_name = "LunaLan07/BioHiCL-base"
-model = SentenceBERT(model_name)
+model = SentenceTransformer(model_name)
 
+# Retrieval
 retriever = DenseRetrievalExactSearch(model, batch_size=16)
 results = retriever.search(corpus, queries, top_k=10, score_function="cos_sim")
 
+# Evaluation
 ndcg, _map, recall, precision = EvaluateRetrieval.evaluate(
     qrels, results, k_values=[1, 3, 5, 10]
-)
-
-
+)