MétaCan
Menu
Back to cohort

From GPT to LLaMA: Tracing the Growth of Large Language Models

2025· article· W4415926346 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

VenueTheoretical and Natural Science · 2025
Typearticle
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsLEAPSLanguage modelScalingTracingKey (lock)Natural languageScaling law

Abstract

fetched live from OpenAlex

Large Language Models (LLMs) have transformed natural language processing by scaling model parameters to unprecedented levels. This review traces the historical progression of LLM parameter sizes, from early pre-trained models with millions of parameters to today’s multi-billion and even trillion-parameter systems. We examine key breakthroughs in scaling (e.g., the GPT series, PaLM, LLaMA), highlighting how increasing model size has led to emergent capabilities in language understanding and generation. We also discuss the engineering innovations, such as Transformer architectures and mixture-of-experts, that enabled these leaps in scale. A comparative analysis is provided, including a table and trend figure, to illustrate growth in parameter counts over time and across model families. We further explore the implications of model size on performance, emergent behaviors, and computational cost, noting scaling laws and diminishing returns. Finally, we discuss future directions, arguing that while scaling has driven progress, challenges in efficiency, alignment, and data quality will shape the next phase of LLM development.

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)0.002
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.247
Threshold uncertainty score0.930

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.003
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.026
GPT teacher head0.391
Teacher spread0.365 · 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