Saved in:
Bibliographic Details
Main Authors: Garcia, Gabriel Lino, Manesco, João Renato Ribeiro, Paiola, Pedro Henrique, Miranda, Lucas, de Salvo, Maria Paola, Papa, João Paulo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.03531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917857035550720
author Garcia, Gabriel Lino
Manesco, João Renato Ribeiro
Paiola, Pedro Henrique
Miranda, Lucas
de Salvo, Maria Paola
Papa, João Paulo
author_facet Garcia, Gabriel Lino
Manesco, João Renato Ribeiro
Paiola, Pedro Henrique
Miranda, Lucas
de Salvo, Maria Paola
Papa, João Paulo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03531
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences
Garcia, Gabriel Lino
Manesco, João Renato Ribeiro
Paiola, Pedro Henrique
Miranda, Lucas
de Salvo, Maria Paola
Papa, João Paulo
Computation and Language
Machine Learning
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.
title A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2412.03531