MétaCan
Menu
Back to cohort

Text2Graph: A Method for Automatically Drawing Statistical Graphs Based on Large Language Models

2025· article· W7130353007 on OpenAlexaff
Chunhui He, Bin Ge, Zhihan Zhou, Chong Zhang

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicData Visualization and Analytics
Canadian institutionsUniversity of British Columbia
FundersNational Natural Science Foundation of China
KeywordsVisualizationProcess (computing)Statistical modelGraph drawingGraphNatural languageData visualizationVisual language

Abstract

fetched live from OpenAlex

With the in-depth development of digitalization and informatization, data visualization technology is undergoing unprecedented changes. As an important tool of data visualization, statistical graphs have been widely used in various fields. However, the traditional statistical graph drawing process is heavily dependent on the operation skills of professionals, and there are some problems such as cumbersome process and low efficiency. Therefore, an automatic drawing method of statistical graphs based on large language model is innovatively proposed and named Text2Graph. Via deeply integrating large language model technology to carry out end-to-end automatic generation from natural language instructions to visual statistical graphics. Text2Graph covers three core modules: intelligently identifying users' drawing requirements, automatically generating and assembling drawing codes, and automatically executing drawing scripts. The experimental results show that Text2Graph method performs well in eight conventional statistical graph automatic drawing tasks under specific compilation environment, and the qualified rate and excellent rate of automatic drawing reach 100% and 80% respectively. It can greatly enhance the intelligent level and efficiency of statistical graph drawing.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.019
Threshold uncertainty score0.064

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0040.003
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0190.007

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.024
GPT teacher head0.378
Teacher spread0.354 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicData Visualization and AnalyticsFrench-language works237,207