---
license: apache-2.0
datasets:
- BeIR/scidocs
- miriad/miriad-4.4M
- BioASQ-b
language:
- en
base_model:
- BAAI/bge-reranker-v2-gemma
pipeline_tag: text-ranking
tags:
- medical
- rerank
---

# MedSwin/MedSwin-Reranker-bge-gemma — Fine-tuned Biomedical & EMR Context Ranking

- **Developed by:** Medical Swinburne University of Technology AI Team
- **Funded by:** [Swinburne University of Technology](https://www.swinburne.edu.au)
- **Language(s):** English
- **License:** Apache 2.0

## Overview
1. **RAG Context Reranking**  
   Re-rank candidate passages retrieved from a VectorDB (initial recall via embeddings), improving final context selection for downstream medical LLM reasoning.

2. **EMR Profile Reranking**  
   Re-rank patient historical information (e.g., past assessments, diagnoses, medications) to surface the most clinically relevant records for a given current assessment.

The reranker outputs a **direct relevance score** for each *(query, passage)* pair and can be used as a drop-in “second-stage” ranking component after embedding-based retrieval.

---

## Why a Reranker?
Embedding retrieval is fast and scalable but may miss nuanced relevance (clinical relationships, subtle terminology, long context dependencies).  
A reranker improves precision by explicitly scoring each candidate passage against the query, typically yielding better top-k context for medical QA and decision support.

---

## Base Model
- **Model**: [BAAI/bge-reranker-v2-gemma](https://huggingface.co/BAAI/bge-reranker-v2-gemma)
- **Finetuning strategy**: **LoRA** (parameter-efficient fine-tuning) with gradient checkpointing and mixed precision (fp16/bf16 depending on GPU).
- **Rationale**: Gemma-based rerankers generally provide strong relevance modeling and support longer contexts compared to smaller rerankers.

---

## Training Data (Offline, Local)
We fine-tune using **open HF datasets** stored locally on HPC:

### 1) BioASQ (Generated Queries)
- Used as: (query, document) positives; negatives sampled from rolling buffer.
- Specialised to handle the complex terminology and high precision required for Task B (Biomedical Semantic QA). The reranker acts as a critical second stage in a two-stage retrieval system, filtering initial candidate lists from a PubMed-indexed retriever to ensure the highest-ranked documents contain the specific evidence needed for factoid and 'ideal' answer generation.
  
### 2) MIRIAD (Medical IR Instruction Dataset)
- Used as: (question → passage) positives; negatives sampled from rolling buffer.
- [MIRIAD's 4.4M](https://huggingface.co/datasets/miriad/miriad-4.4M) literature-grounded QA pairs, the model is trained to distinguish between highly similar clinical concepts. This specialization reduces medical hallucinations and ensures that the most scientifically accurate evidence is prioritised in a multi-stage retrieval pipeline for healthcare professionals. 

### 3) SciDocs 
- Multi-task dataset—including citation prediction and co-citation analysis—the model learns to capture nuanced semantic relationships that standard Bi-Encoders miss. The resulting reranker serves as a high-accuracy second stage in a two-stage retrieval pipeline, significantly improving Top-K relevance for complex scholarly queries.

---

## Methodology
### Data Construction (Triplets)
The training corpus is converted into reranker triplets:
```json
{
  "query": "clinical question",
  "pos": ["relevant passage 1", "relevant passage 2"],
  "neg": ["irrelevant passage A", "irrelevant passage B"],
  "source": "dataset_name"
}
```

* **Positives**: from dataset relevance labels or paired question–passage examples.
* **Negatives**: sampled from an in-memory rolling buffer (fast, scalable offline).
* Output splits: **train / val / test** created in one run.

### Evaluation

Computes IR ranking metrics by scoring each query against its *(pos + neg)* candidates:

* **nDCG@10:** 0.60+
* **MRR@10:** 0.50+ 
* **MAP@10:** 0.40+
* **Hit@1:** 0.40+
* Metrics reported overall and broken down by data source.