The study audits AI "humanizers"—tools that rewrite machine‑generated text to evade detection—by checking whether factual units such as numbers, dates, names, and quoted spans survive each rewrite. Using a rule‑based checker validated by AI annotators, the authors found that in the 2026 public leaderboard, 35–65% of documents had at least one factual unit altered or dropped, with quoted spans most affected. An open 12B humanizer retained most numbers and names but reworded 67–78% of quotes, and a zero‑shot detector (Jev) could distinguish human originals from humanized rewrites with an AUROC of 0.864, outperforming several existing detectors.
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).
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...
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.
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.
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."
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.
arXiv:2608. 11256v1 Announce Type: new Abstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct.
The paper audits the widely used ISOT/Kaggle Fake and Real News corpus and finds that extremely high reported accuracies (≈0.98) are largely due to shortcut signals rather than genuine veracity detection. A simple TF‑IDF linear classifier achieves perfect F1 when using only subject metadata, and even after removing metadata, newswire tags, and duplicate documents, the F1 drops only modestly, indicating that editorial style rather than specific tokens drives performance. Under topic‑disjoint and temporal transfer tests, performance collapses, and models transfer poorly to the independent LIAR benchmark, showing that within‑corpus scores reflect source and topic separability, not truth verification. whyItMatters:"The study demonstrates that current high accuracy metrics on this fake‑news dataset are misleading, highlighting the need for more robust evaluation protocols that guard against shortcut learning."
arXiv:2608. 00144v2 Announce Type: replace Abstract: Membership inference (MIA) on language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate members from non-members using surface text alone.
GPT4o-Receipt is a benchmark dataset of 1,235 receipt images that pairs GPT‑4o‑generated receipts with authentic ones from established datasets. The study evaluates five state‑of‑the‑art multimodal LLMs and a 30‑annotator crowdsourced perceptual study, revealing that humans are better at spotting AI artifacts yet perform worse at binary detection than models like Claude Sonnet 4 and Gemini 2.5 Flash. The paradox is explained by the fact that the dominant forensic signals—arithmetic errors—are invisible to visual inspection but can be quickly verified by LLMs.
The study evaluates machine‑generated text detectors on scientific literature, finding that many detectors perform near perfectly on certain benchmarks due to superficial formatting cues rather than genuine linguistic differences. A logistic regression using 27 superficial features achieved macro‑F1 scores between 0.833 and 0.997, outperforming other detectors on arXiv subsets. The most powerful cue was the PDF extraction artifact—human texts preserve line breaks while generated texts appear as a single block—allowing classification at 0.996 AUC. By introducing format counterfactuals and normalizing formatting, the authors demonstrate that re‑wrapping machine‑written abstracts can flip 20–27% of detector decisions, reducing the generalization gap and improving out‑of‑domain performance.
arXiv:2601. 20336v5 Announce Type: replace-cross Abstract: Do the functional narratives in cryptocurrency whitepapers correspond to how their tokens behave in markets?