通过快速工程,将化学知识集成到大型语言模型中
Hongxuan Liu1, Haoyu Yin1, Zhiyao Luo2
1Department of Chemical Engineering, Tsinghua University, Beijing, 100084, China.
Synthetic and systems biotechnology
|August 29, 2024
概括
将特定领域的知识集成到快速工程中,可以显著提高大语言模型 (LLM) 在科学中的性能. 这种领域知识嵌入式方法提高了准确性,并减少了科学发现的幻觉.
科学领域:
- 人工智能的人工智能
- 计算化学计算化学
- 材料科学 材料科学 材料科学
背景情况:
- 大型语言模型 (LLM) 显示出科学应用的前景,但需要专业知识才能达到最佳性能.
- 传统的快速工程方法可能无法充分利用LLM在复杂的科学领域的潜力.
- 将特定领域的信息整合到提示中对于提高LLM在科学环境中的准确性和相关性至关重要.
研究的目的:
- 调查领域特定知识整合在大型语言模型 (LLM) 快速工程中的影响.
- 为科学应用开发和评估一个嵌入域知识的快速工程方法.
- 使用关键性能指标,将拟议的方法与传统的提示工程策略进行比较.
主要方法:
- 开发一种新的领域知识嵌入式快速工程技术.
- 该方法应用于复杂的科学案例研究,包括麦克米兰催化剂,帕克利塔塞尔和氧化物.
- 使用能力,准确性,F1得分和幻觉减少等指标进行定量评估.
主要成果:
- 与传统方法相比,域知识嵌入式提示工程方法表现出卓越的性能.
- 在准确性,F1得分和幻觉显著减少方面观察到显著的改善.
- 案例研究证实了该方法在处理复杂的科学材料和产生可靠的输出方面的有效性.
结论:
- 特定领域的提示有效地引导LLM产生更准确和更相关的科学信息.
- 拟议的方法增强了LLM作为科学发现和创新的强大工具的实用性.
- 对特定领域的提示工程进行进一步的研究是有必要的,以释放LLM在科学中的全部潜力.
相关概念视频
Chemical Equations
63.1K
Chemical equations represent the identities and relative quantities of substances involved in a chemical reaction. The substances undergoing reaction are called reactants, and their formulas are placed on the left side of the equation. The substances generated by the reaction are called products, and their formulas are placed on the right side of the equation. Plus signs (+) separate individual reactant and product formulas, and an arrow (→) separates the reactant and product (left and...
63.1K
Predicting Reaction Outcomes
8.3K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.3K
Chemical Symbols
8.3K
A chemical symbol is an abbreviation that is used to indicate an element or an atom of an element. For example, the symbol for mercury is Hg. We use the same symbol to indicate one atom of mercury (microscopic domain) or to label a container of many atoms of the element mercury (macroscopic domain).
Some symbols are derived from the common name of the element; others are abbreviations of the name in another language. Most symbols have one or two letters, but three-letter symbols have been used...
Some symbols are derived from the common name of the element; others are abbreviations of the name in another language. Most symbols have one or two letters, but three-letter symbols have been used...
8.3K
Chemical Reactions
9.8K
A balanced chemical equation provides the information of chemical formulas of the reactants and products involved in the chemical change. A reaction’s stoichiometry helps predict how much of the reactant is needed to produce the desired amount of product, or in some cases, how much product will be formed from a specific amount of the reactant.
The relative amounts of reactants and products represented in a balanced chemical equation are often referred to as stoichiometric amounts.
The relative amounts of reactants and products represented in a balanced chemical equation are often referred to as stoichiometric amounts.
9.8K
Electrophilic Aromatic Substitution: Overview
10.9K
In an electrophilic aromatic substitution reaction, an electrophile substitutes for a hydrogen of an aromatic compound.
10.9K
Inductive Effects on Chemical Shift: Overview
1.1K
The protons in unsubstituted alkanes are strongly shielded with chemical shifts below 1.8 ppm. Methine, methylene, and methyl protons appear at approximately 1.7, 1.2 and 0.7 ppm, while the proton signal from methane appears at 0.23 ppm. An electronegative substituent, such as chlorine, withdraws the electron density from the protons, increasing their chemical shift. Progressive substitution of the hydrogens in methane by chlorine shifts the proton signals increasingly downfield, to 3.05 ppm in...
1.1K


