Metraipolis › archive › dc_b9712970d95e

NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text — arXiv:2610.41459

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41459
License (as archived)
CC0-1.0
Archived
2026-11-03T05:40:51.193Z
SHA-256 of the archived text
7e109e47a45a4845df6ee40f082ed1fd34d5e781356a1de69acd0a12923fc97c
Stable URL of this page
https://metraipolis.com/documento/dc_b9712970d95e

How to cite

NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text — arXiv:2610.41459 — arXiv (en), https://arxiv.org/abs/2610.41459 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9712970d95e (Metraipolis archive dc_b9712970d95e, sha256 7e109e47a45a4845df6ee40f082ed1fd34d5e781356a1de69acd0a12923fc97c)
BibTeX
@misc{dcb9712970d95e,
  title = {NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text — arXiv:2610.41459},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41459},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9712970d95e; sha256 7e109e47a45a4845df6ee40f082ed1fd34d5e781356a1de69acd0a12923fc97c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41459. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Web platforms screen posts for text written by large language models, and every false flag hits a human writer. Detectors must therefore run at a very low false positive rate (FPR). Zero-shot detectors such as Binoculars score text with frozen language models, but invisible edits such as homoglyphs shatter tokenization and push machine text into the human range. Unicode normalization undoes these edits, yet the normalized score still misses half of the machine text at a strict FPR, under attacks that leave nothing to clean. We find that with the Falcon-7B scoring pair, heads on token statistics recall less than the normalized score at this FPR, and several flag too many human posts in some sections. We propose NormDetect, which anchors a learned per-section head to the normalized zero-shot score. A blend weight chosen on training folds under a human FPR cap combines the two scores, and one threshold is calibrated on human text only. On eight sections of the RAID benchmark with eleven attacks, NormDetect raises recall at a 0.1% calibrated FPR by 5.0 points over normalized Binoculars. Its human FPR bound stays at most 1% in every section, and no other detector within this bound recalls as much.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41459 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T05:26:25.692Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).