arXiv:2608. 14843v1 Announce Type: cross Abstract: As authorship attribution systems are increasingly deployed to detect ghostwritten and AI-generated papers, their errors can support accusations against legitimate authors.
arXiv:2608. 19746v1 Announce Type: new Abstract: Personalized text generation aims to make LLMs write in a specific individual's style, yet existing benchmarks measure task accuracy or preference alignment rather than whether the model's output actually resembles the target author's writing.
arXiv:2606. 00545v1 Announce Type: new Abstract: Post-trained language models can recognize their own outputs from a sentence or two out of context.
The study investigates whether AI assistance leaves a temporal fingerprint in writing and programming tasks. By analyzing keystroke-level data from three corpora, the authors find that AI contributions appear in distinct bursts and that temporal patterns can almost perfectly distinguish wholesale delegation from authentic work, though ordinary collaboration remains hard to detect. The research suggests that process visibility could serve as a basis for academic integrity checks.
arXiv:2608. 05157v1 Announce Type: cross Abstract: Double blind peer review serves as the scientific community primary defense against status and affiliation bias.
These names do not exist. Elena Vasquez and Marcus Chen have appeared as volcano experts, astronauts, thriller protagonists, podcast hosts, and academic co-authors across hundreds of independently produced AI-generated documents, never having lived.
arXiv:2609.38831v1 Announce Type: new Abstract: Model-attribution classifiers can often identify which language model produced a text, making model-specific writing patterns a signal of provenance. A...
arXiv:2606. 02184v1 Announce Type: cross Abstract: These names do not exist.
The paper investigates whether language models can identify sentences from their training data by using exact duplication counts from publicly released corpora for two model families, OLMo‑2 and Pythia. It finds that for typical duplication levels, models show only a weak trace of exposure, with a rank correlation near –0.08, and that strong signals only appear when a sentence appears roughly a thousand times, at which point fame rather than memory dominates. The study also demonstrates that common membership tests can be misleading, as changing a single word does not alter the model’s preference, and that controlling for register can significantly improve detector performance.
arXiv:2508. 01656v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult.
arXiv:2609.06771v1 Announce Type: cross Abstract: Authorship signals matter in settings where writing style carries identity: digital forensics, plagiarism analysis, account linking, misinformation i...
arXiv:2609.01432v1 Announce Type: cross Abstract: Scientific citations carry rhetorical intent. Scholars may cite prior work positively (supporting), negatively (contrasting), or neutrally (mentionin...
The paper audits a 366‑day autobiographical book generated by a large language model (LLM) against an independent verification corpus. Using a four‑level rubric, 354 of the 366 days (96.7%) failed verification, with only 12 days containing corroborated scenes and 19 days containing actively contradicted claims. Regenerating the same days with current models yielded 100% verification failure, while grounding the generation in the subject’s own corpus improved the rate to 83.3% but still left substantial residual failure.