Claim · 2019 · event · Stated in source · Supported

Radford et al. (2019) report a Transformer-based architecture, citing Vaswani et al., for the GPT-2 language models.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Language Models are Unsupervised Multitask Learners → reports using method from → Attention Is All You Need

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Language Models are Unsupervised Multitask Learnersreports using method from ↓Attention Is All You Need

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2019 · event Records dated 2019 →

Scope and limitsThe paper also states that the model largely follows the earlier OpenAI GPT model (Radford et al., 2018).

The evidence 01

primary sourceSupports the claim

Language Models are Unsupervised Multitask Learners

OpenAI · Publication date unknown

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“We use a Transformer (Vaswani et al., 2017) based architecture for our LMs.”

Location in source PDF p. 4, section 2.3

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Alec Radford; Jeffrey Wu; Rewon Child; David Luan; Dario Amodei; Ilya Sutskever
Version: Technical paper PDF served by OpenAI; the PDF prints no date. OpenAI’s announcement of 14 February 2019 links it (cross-family check, item A002). Retrieved for the candidate pack on 2026-10-28 (SHA-256 d9d852e2894556e73f53cb22b7c605a9643d6f0b19bf604b429ed6192fa24f4e). The author list is the byline as printed on the first page.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, “Language Models are Unsupervised Multitask Learners”.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Kinds of AI and technical history (research/technical-history). The quotation (13 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes, PDF line-break hyphens and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (31 October 2026, item 127) re-read the record’s sources and found that they support what the record states. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A document explicitly reports using an identified method or architecture from another work in its own study. Requires a named method and primary evidence from the reporting document. Citation, comparison, proposed future use and similarity alone do not qualify. This is reported use, not independently verified implementation or institutional adoption.

Date. Date as a later account or citation gives it; no contemporaneous text read here dates it. Year from a later citation (claimed); the PDF is undated.

Record ID th-fam-tllm-gpt2-uses-transformer