Methods › Natural Language Processing › Language Models › GPT-4

GPT-4

2,870 papers tagged archive 2025-07-28

Introduced by OpenAI et al. in GPT-4 Technical Report

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

GPT-4 is a transformer based model pre-trained to predict the next token in a document.

PaperSource

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 1 entry in Syntology's graph carry it; the most cited is the paper “Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing” (arXiv:2305.03195, 91 citations). None of them is well cited, so for any better known sense of the name this is still a gap in coverage; they are listed so you can judge, not as a substitute. For arXiv:2305.03195: ask the lookup about it.

Near matches the lookup lists, each a different name: GPT; GPT-D; H-GPT; RF-GPT; MS-GPT; GPT-RE; VA-GPT; GPT-ST.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 2,870 · with a code link: 1,244 · where Syntology ran a sample: 526 (387 with a run with no instrument failure, 139 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (526 of 2,870 tagged: 387 with a run with no instrument failure, 139 where every run was a failure of Syntology's instrument)

Page 1 of 29: papers 1 to 100 of 2,870, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 734 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 Modelling447
Language Modeling322
Large Language Model298
Question Answering251
Retrieval167
Decision Making122
In-Context Learning121
Benchmarking120
RAG111
Code Generation110
Retrieval-augmented Generation109
Prompt Engineering105
Text Generation99
Math94
Hallucination87
Multiple-choice79
Sentence69
Instruction Following68
Mathematical Reasoning58
Chatbot57

Usage over time archive 2025-07-28

Papers per year tagged with GPT-4: 2023 to 2025, peak 1,637 1,637 0 2023: 883 papers 2023 2024: 1637 papers 2024 2025: 350 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (2,870 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

Language Models

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