联合知识检索提高了生物医学基准上的大型语言模型性能
1Department of Integrative Structural and Computational Biology, Scripps Research, La Jolla, CA, USA.
bioRxiv : the preprint server for biology
|August 6, 2025
概括
使用BioThings Explorer (BTE-RAG) 进行检索增强生成,通过整合明确证据,增强机械探索和翻译应用,显著提高生物医学研究中的大语言模型准确性.
科学领域:
- 生物医学信息学 生物医学信息学
- 人工智能在医学中的应用
- 计算生物学 计算生物学
背景情况:
- 大型语言模型 (LLM) 在生物医学自然语言处理方面表现有前途.
- 由于依赖统计模式,LLM经常产生事实上的不准确性 (幻觉).
- 这些不准确性在关键的生物医学应用中构成风险.
研究的目的:
- 开发和评估一种新的检索增强生成框架,BTE-RAG.
- 提高生物医学研究中LLMs的准确性和可靠性.
- 为了利用明确的机械学证据来提高LLM的性能.
主要方法:
- 开发了BTE-RAG,将LLMs与BioThings Explorer的API联合体集成在一起.
- 从DrugMechDB创建了三组基因中心机制,代谢物效应和药物与生物过程关系的基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因基因
- 系统地评估了BTE-RAG与LLM-only方法的比较,使用GPT-4o和GPT-4o mini.
主要成果:
- 通过BTE-RAG,基因中心精度从51%提高到75.8% (GPT-4o mini) 和69.8%提高到78.6% (GPT-4o).
- 代谢物效应问题相似度得分 (>=0.90) 增加了82% (GPT-4o mini) 和77% (GPT-4o).
- 药物生物过程一致性得到改善,GPT-4o的高一致性答案增加了>10%.
结论:
- 联合知识检索可以提高生物医学环境中的LLM准确性.
- BTE-RAG为机械勘探提供了透明的改进.
- BTE-RAG是翻译生物医学研究的一个实用工具.
相关概念视频
02:07Improving Translational Accuracy
2.7K
2.7K
01:10Higher Mental Functions of the Brain: Language
1.0K
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
1.0K
01:45ER Retrieval Pathway
3.9K
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
3.9K
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
126
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
126
01:37Super-resolution Fluorescence Microscopy
7.7K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
7.7K
01:26Pharmacokinetic Models: Comparison and Selection Criterion
149
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
149