arXiv:2607. 29539v1 Announce Type: cross Abstract: Standard AI-text detection benchmarks compare human-written text against text generated directly by large language models (LLMs).
By Gaetano Perrone, Simon Pietro Romano
arXiv:2609.15369v1 Announce Type: new
Abstract: Word-level detectors identify unedited AI-generated text almost perfectly, but the literature documents their brittleness under rewording, and a word-l...
By Jochen Madler (Sitefire)
The study examines how the rapid turnover of large language models (LLMs) undermines the effectiveness of AI‑detectors used to screen scientific manuscripts. By comparing 4,000 PNAS abstracts rewritten by 23 different LLM versions released between June 2023 and August 2026, the authors show that detectors trained on past versions can fail dramatically at generation boundaries, missing up to 96% of rewrites just after a sharp transition. Even detectors updated to newer versions can overlook rewrites of older models, and a commercial detector missed most rewrites of the newest version while flagging few human‑written abstracts.
By Kazuki Nakajima, Takayuki Mizuno
arXiv:2608. 10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.
By Scott E. Frias
The paper argues that current AI‑text detection methods, which estimate human contribution by measuring how predictive a user’s prompt is of the final text, can be easily manipulated. By introducing SPECIFICITY PADDING—adding random IDs to the prompt—the authors show that a title‑only request can appear far more human than one containing the article’s key ideas, and that scores can swing dramatically when the evaluator’s view of the prompt is altered. Across a range of large language models, the same documents can be scored as 85 % human or 15 % human depending solely on the prompt used, revealing a fundamental limitation of likelihood‑based metrics for reliably measuring human authorship.
whyItMatters":"The study demonstrates that likelihood‑based scores cannot reliably establish human contribution without additional evidence of what the person added and how the text was produced."
By Hasan Amin, Zhuoran Lu, Ming Yin
arXiv:2608. 00144v1 Announce Type: new Abstract: Membership inference (MIA) on language models is usually summarised by an aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines separate members from non-members from surface text alone.
By Victor Maricato