MEG: Medical Knowledge-Augmented Large Language Models for Question Answering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915253597503488 |
|---|---|
| author | Cabello, Laura Martin-Turrero, Carmen Akujuobi, Uchenna Søgaard, Anders Bobed, Carlos |
| author_facet | Cabello, Laura Martin-Turrero, Carmen Akujuobi, Uchenna Søgaard, Anders Bobed, Carlos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03883 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MEG: Medical Knowledge-Augmented Large Language Models for Question Answering Cabello, Laura Martin-Turrero, Carmen Akujuobi, Uchenna Søgaard, Anders Bobed, Carlos Computation and Language Artificial Intelligence Machine Learning 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. |
| title | MEG: Medical Knowledge-Augmented Large Language Models for Question Answering |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.03883 |