MétaCan
Menu
Back to cohort
Record W4388380341 · doi:10.31234/osf.io/dc6tz

Evaluating Large Language Models for Assisting in Meta-Analysis

2023· preprint· en· W4388380341 on OpenAlexaff
Feng Ji, Jiayi Han, Yuchen Zhang, Shi’ting Chen, Jinbo He

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversity of Toronto
FundersNational Natural Science Foundation of China
KeywordsCoding (social sciences)Meta-analysisComputer scienceQualitative analysisPerspective (graphical)Empirical researchQualitative propertyQuantitative analysis (chemistry)Natural language processingData scienceQualitative researchPsychologyArtificial intelligenceMachine learningStatisticsSocial scienceSociologyMedicinePathology

Abstract

fetched live from OpenAlex

Large language models (LLMs) are receiving increased attention in academia as aids for scientific research due to their superior performance in tasks related to natural language processing and understanding. Meta-analysis, a research method involving extensive text processing to extract and code qualitative and quantitative information from empirical studies, is particularly well-suited to the application of LLMs. In this study, we empirically evaluated the ability of LLMs to perform automatic coding tasks within meta-analytic contexts, using Bing Chat (based on GPT-4.0) and ChatPDF (based on GPT-3.5) as examples. Our findings indicate that Bing Chat outperformed ChatPDF in accurately extracting and coding qualitative information such as publication type, country, and survey methods. However, its performance decreased when handling quantitative data, such as correlation coefficients. We also noted an upward trend in Bing Chat's performance over time. The potential and utility of LLMs in facilitating meta-analysis from a researcher’s perspective are further discussed.

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)0.389
metaresearch head score (Gemma)0.659
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.611
Threshold uncertainty score0.753

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.3890.659
Meta-epidemiology (narrow)0.0070.004
Meta-epidemiology (broad)0.0060.023
Bibliometrics0.0200.016
Science and technology studies0.0030.002
Scholarly communication0.0130.011
Open science0.0050.008
Research integrity0.0040.006
Insufficient payload (model declined to judge)0.0050.001

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 head0.485
GPT teacher head0.456
Teacher spread0.029 · 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.

Study designSimulation or modeling
DomainMethods
GenreEmpirical

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
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207