MétaCan
Menu
Back to cohort
Record W4414132264 · doi:10.1017/rsm.2025.10031

StudyTypeTeller—Large language models to automatically classify research study types for systematic reviews

2025· article· en· W4414132264 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueResearch Synthesis Methods · 2025
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsMcMaster University
FundersUniversität ZürichSchweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
KeywordsGenerative grammarTransformerSystematic reviewLanguage modelScientific literatureEncoder

Abstract

fetched live from OpenAlex

screening, a labor-intensive aspect of systematic review, is increasingly challenging due to the rising volume of scientific publications. Recent advances suggest that generative large language models like generative pre-trained transformer (GPT) could aid this process by classifying references into study types such as randomized-controlled trials (RCTs) or animal studies prior to abstract screening. However, it is unknown how these GPT models perform in classifying such scientific study types in the biomedical field. Additionally, their performance has not been directly compared with earlier transformer-based models like bidirectional encoder representations from transformers (BERT). To address this, we developed a human-annotated corpus of 2,645 PubMed titles and abstracts, annotated for 14 study types, including different types of RCTs and animal studies, systematic reviews, study protocols, case reports, as well as in vitro studies. Using this corpus, we compared the performance of GPT-3.5 and GPT-4 in automatically classifying these study types against established BERT models. Our results show that fine-tuned pretrained BERT models consistently outperformed GPT models, achieving F1-scores above 0.8, compared to approximately 0.6 for GPT models. Advanced prompting strategies did not substantially boost GPT performance. In conclusion, these findings highlight that, even though GPT models benefit from advanced capabilities and extensive training data, their performance in niche tasks like scientific multi-class study classification is inferior to smaller fine-tuned models. Nevertheless, the use of automated methods remains promising for reducing the volume of records, making the screening of large reference libraries more feasible. Our corpus is openly available and can be used to harness other natural language processing (NLP) approaches.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.128
metaresearch head score (Gemma)0.051
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.949
Threshold uncertainty score0.957

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.1280.051
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.003
Science and technology studies0.0010.000
Scholarly communication0.0010.000
Open science0.0040.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.474
GPT teacher head0.598
Teacher spread0.124 · 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