Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Gabriel Lino Garcia, João Renato Ribeiro Manesco, Pedro Henrique Paiola, Lucas Miranda, Maria Paola de Salvo, João Paulo Papa

TL;DR

This paper surveys how large language models (LLMs) are applied to biomedical evidence synthesis and knowledge extraction amid rapidly expanding literature. It reviews tasks from literature-based discovery and data extraction to complex QA, highlighting models such as GPT-3.5/4, Claude 2, RoBERTa, and BioBERT, and retrieval strategies including RAG. Key findings reveal persistent challenges including hallucinations, contextual understanding, bias from training data, and a lack of unified benchmarks for fair comparison. The authors advocate future directions that emphasize retrieval-augmented generation, knowledge-grounded reasoning, and standardized benchmarks to enable reliable real-world deployment in healthcare.

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.

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

TL;DR

This paper surveys how large language models (LLMs) are applied to biomedical evidence synthesis and knowledge extraction amid rapidly expanding literature. It reviews tasks from literature-based discovery and data extraction to complex QA, highlighting models such as GPT-3.5/4, Claude 2, RoBERTa, and BioBERT, and retrieval strategies including RAG. Key findings reveal persistent challenges including hallucinations, contextual understanding, bias from training data, and a lack of unified benchmarks for fair comparison. The authors advocate future directions that emphasize retrieval-augmented generation, knowledge-grounded reasoning, and standardized benchmarks to enable reliable real-world deployment in healthcare.

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.

Paper Structure

This paper contains 9 sections, 1 figure, 1 table.

Table of Contents

  1. INTRODUCTION
  2. Review Methodology
  3. Screening of Relevant Works
  4. Background
  5. Results
  6. Evidence Synthesis
  7. Synthesis in Biomedical Sciences
  8. Comparison of Current Methods and Future Directions
  9. Conclusion

Figures (1)

  • Figure 1: Illustration of the screening process, conducted in accordance with the PRISMA protocol, used to identify and select relevant studies for this review.