disi-unibo-nlp/medgenie
The First Generate-then-Read Framework for Multiple-Choice Question Answering in Medicine
Generated contexts enhance medical QA through domain-specific language models (PMC-LLaMA-13B) that create relevant passages before answer selection, eliminating dependency on retrieval. The framework offers two reader variants—Fusion-in-Decoder (FID) for supervised learning with 250M parameters and in-context learning with LLaMA-2/Zephyr-7B—operating efficiently within 24GB VRAM on MedQA-USMLE, MedMCQA, and MMLU medical subsets. Multi-view context generation combines question-focused and option-focused perspectives to improve answer accuracy.
No commits in the last 6 months.
Stars
13
Forks
2
Language
Python
License
—
Category
Last pushed
May 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/disi-unibo-nlp/medgenie"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Rohan-Thoma/Multiple-choice-question-generator-using-NLP
Project aims at generating multiple choice questions along with the options and correct answer...
priyam-hub/TestPaperPro
The Dynamic Test Paper Generator using Bloom's Taxonomy is a Streamlit-based application that...
Azazel0203/MCQ_GENERATOR
The "MCQ Generator with Streamlit" web app utilizes OpenAI's language models to create...
rhythmd18/SmartClarify
An AI-based doubt solving app designed for students. Built using the Google's Gemini Pro model.
muhammadadilnaeem/MCQ-Generator-using-OpenAI-Langchain-Streamlit
The MCQ Generator is a comprehensive project designed to generate multiple-choice questions...