A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences

TL;DR

This review discusses how large language models are transforming biomedical knowledge extraction, highlighting their potential, current challenges, and future research directions to improve healthcare information access.

Contribution

It provides a comprehensive overview of LLM applications in biomedical knowledge extraction, identifying gaps and proposing integration of advanced techniques like RAG.

Findings

LLMs show promise in automating biomedical data extraction.

Challenges include hallucinations and limited generalization.

Future directions involve standardizing benchmarks and improving model reliability.

Abstract

The rapid advancement of large language models (LLMs) has opened new boundaries in the extraction and synthesis of medical knowledge, particularly within evidence synthesis. This paper reviews the state-of-the-art applications of LLMs in the biomedical domain, exploring their effectiveness in automating complex tasks such as evidence synthesis and data extraction from a biomedical corpus of documents. While LLMs demonstrate remarkable potential, significant challenges remain, including issues related to hallucinations, contextual understanding, and the ability to generalize across diverse medical tasks. We highlight critical gaps in the current research literature, particularly the need for unified benchmarks to standardize evaluations and ensure reliability in real-world applications. In addition, we propose directions for future research, emphasizing the integration of state-of-the-art techniques such as retrieval-augmented generation (RAG) to enhance LLM performance in evidence synthesis. By addressing these challenges and utilizing the strengths of LLMs, we aim to improve access to medical literature and facilitate meaningful discoveries in healthcare.