Question answering is a natural language understanding task that involves reasoning over both explicit context, and unstated relevant domain knowledge. Despite the high cost of training, large language models (LLMs) -- the backbone of most modern question-answering systems -- still struggle to reliably capture the nuanced relationships between concepts that are crucial for reasoning in specialized fields like medicine. In this work, we present MEG, a parameter-efficient approach for medical knowledge-augmented LLMs. MEG uses a lightweight mapping network to incorporate knowledge graph embeddings into the LLM, enabling it to leverage external knowledge in a cost-effective way. We evaluate our method on four popular medical multiple-choice datasets and show that LLMs i) can effectively interpret knowledge graph embeddings and ii) gain significant advantages from the factual grounding these embeddings provide. MEG attains an average of +6.7% and +9.9% accuracy over specialized models like BioMistral-7B and MediTron-7B, respectively. Finally, we show that MEG's performance remains robust to the choice of graph encoder.
View on arXiv@article{cabello2025_2411.03883,
title={ MEG: Medical Knowledge-Augmented Large Language Models for Question Answering },
author={ Laura Cabello and Carmen Martin-Turrero and Uchenna Akujuobi and Anders Søgaard and Carlos Bobed },
journal={arXiv preprint arXiv:2411.03883},
year={ 2025 }
}