Methods › Natural Language Processing › Autoregressive Transformers › GPT

GPT

1,212 papers tagged archive 2025-07-28

Introduced by Alec Radford et al. in Improving Language Understanding by Generative Pre-Training

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

GPT is a Transformer-based architecture and training procedure for natural language processing tasks. Training follows a two-stage procedure. First, a language modeling objective is used on the unlabeled data to learn the initial parameters of a neural network model. Subsequently, these parameters are adapted to a target task using the corresponding supervised objective.

Paper

Source in the archive: Improving Language Understanding by Generative Pre-Training, a link on s3-us-west-2.amazonaws.com (archive link, not checked and not linked: not a paper host this site links to).

Papers archive 2025-07-28

30 shown of 1,212, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 583 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling193
Language Modeling138
Large Language Model98
Question Answering71
Text Generation68
Retrieval57
Prompt Engineering52
Sentence50
Decoder45
Decision Making38
Translation35
In-Context Learning34
Text Classification34
text-classification33
Articles31
Few-Shot Learning31
RAG31
Retrieval-augmented Generation31
Fairness30
Natural Language Understanding29

Usage over time archive 2025-07-28

Papers per year tagged with GPT: 2018 to 2025, peak 515 515 0 2018: 1 paper 2018 2019: 28 papers 2019 2020: 23 papers 2020 2021: 50 papers 2021 2022: 62 papers 2022 2023: 360 papers 2023 2024: 515 papers 2024 2025: 173 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,212 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Autoregressive TransformersTransformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections