DracoGPT:从大型语言模型中提取可视化设计偏好
IEEE transactions on visualization and computer graphics
|September 16, 2024
概括
大型语言模型 (LLM) 可能提供不可靠的可视化建议. DracoGPT提取并模拟LLM可视化设计偏好,发现它们通常与基于人类的最佳实践有所不同.
科学领域:
- 计算机科学 计算机科学
- 人与计算机的交互
- 数据可视化 数据可视化
背景情况:
- 在广泛的数据上训练的大型语言模型 (LLM) 可能编码可视化设计知识.
- 然而,他们的学习偏好可能与已建立的最佳实践不一致,导致不可靠的建议.
研究的目的:
- 开发一种方法 (DracoGPT) 来提取,建模和评估LLMs学到的可视化设计偏好.
- 将LLM衍生的偏好与既定的可视化设计准则进行比较.
主要方法:
- 开发了两个管道,DracoGPT-Rank和DracoGPT-Recommend,以建模LLM对排名和推视觉编码规范的偏好.
- 利用Draco,一个共享的知识库,来代表和分析与实证研究准则相对应的LLM偏好.
主要成果:
- DracoGPT准确地模拟了各种LLM的可视化设计偏好.
- 无论是DracoGPT-Rank还是DracoGPT-Recommend,都显示出适度的同意,但与基于人类的实验指南有很大的分歧.
结论:
- LLM表现出不同的可视化设计偏好,可以建模和分析.
- 目前在可视化设计中的LLM偏好与人类验证的最佳实践有很大差异,突出了需要改进的需要.
更多相关视频
05:15The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition
Published on: February 19, 2018
10.8K
09:27Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
Published on: October 13, 2018
9.9K
相关概念视频
Behavioral Genetics and Its Designs
344
Behavior genetics explores how genetic inheritance influences human behavior. It focuses on how genes, passed from parents to offspring, contribute to the development of behavioral traits and tendencies. This branch of genetics seeks to understand the complex interplay between inherited genetic factors and environmental influences in shaping our behaviors.
The primary methodologies used in behavior genetics include family studies, twin studies, and adoption studies, each providing unique...
The primary methodologies used in behavior genetics include family studies, twin studies, and adoption studies, each providing unique...
344
Improving Translational Accuracy
9.4K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.4K
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
3.0K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
3.0K
Study Design in Statistics
7.9K
A study design is a set of techniques that allow a researcher to collect and analyze data from different variables defined for a specific research problem. Statistics is commonly for effective study design and more robust experiments,
Does aspirin reduce the risk of heart attacks? Is one brand of fertilizer more effective at growing roses than another? Is fatigue as dangerous to a driver as the influence of alcohol? Questions like these are answered using randomized experiments with proper...
Does aspirin reduce the risk of heart attacks? Is one brand of fertilizer more effective at growing roses than another? Is fatigue as dangerous to a driver as the influence of alcohol? Questions like these are answered using randomized experiments with proper...
7.9K
Extraction: Advanced Methods
432
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
432
Experimental Designs
11.2K
An experimental design is a systematic process that allows researchers to evaluate the relationship between dependent and independent variables. There are three widely used types of experimental design - pre-experimental design, true experimental design, and quasi-experimental design. In pre-experimental design, the researcher compares the data before and after some interventions or treatments. The true-experimental design has more than one purposefully created group, a commonly measured...
11.2K
