Datasets › MAGE

MAGE

Introduced by Yafu Li et al. in MAGE: Machine-generated Text Detection in the Wild22 May 2023 archive 2025-07-28

The MAGE dataset provides a large set of generated texts using 27 LLMs from seven different groups: OpenAI GPT, LLaMA, GLM130B, FLAN-T5, OPT, BigScience, and EleutherAI. In total, the dataset contains 432,682 texts, along with two additional sets. The first is an additional test set with texts from unseen domains generated by an unseen model, namely GPT-4. The second set is designed to evaluate the robustness of detectors against paraphrasing attacks. To achieve this, the GPT-3.5-turbo model was employed to paraphrase the sentences from the first set, with all paraphrased texts treated as machine-generated.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Binary text classification MAGE (Arbitrary-domains & Arbitrary-models) GigaCheck (Mistral-7B) Average Recall 0.9611 GigaCheck: Detecting LLM-generated Content — 2 Compare

Papers archive 2025-07-28

2 shown of 2 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 11. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
GigaCheck: Detecting LLM-generated Content 0 1 31 Oct 2024 not harvested
MAGE: Machine-generated Text Detection in the Wild 2 1 22 May 2023 ran 0 of 1 samples (1 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • MAGE
  • MAGE (Arbitrary-domains & Arbitrary-models)

2 variant names, as the archive lists them.

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