The study demonstrates that text produced by large language models (LLMs) leaves a distinct stylometric footprint—primarily increased entropy and lexical diversity—across multiple models and domains. In contrast, AI editing of human text does not replicate this footprint; edited texts show only modest lexical diversity gains and reduced entropy, with lexical density emerging as the key distinguishing feature. Consequently, stylometric analysis can differentiate AI-generated from AI-edited content, but is less effective at distinguishing either from purely human writing.
By Zhengyang Shan, Yukyung Lee, Sophie Hao
The paper "Evaluating Style-Personalized Text Generation: Challenges and Directions" examines the difficulties of assessing text that is tailored to individual users’ styles. It critiques common metrics such as BLEU, embeddings, and LLM-as-judges, and introduces a style discrimination benchmark covering domain discrimination, authorship attribution, and LLM-generated personalized versus non-personalized discrimination across eight writing tasks. The study finds that ensembles of diverse evaluation metrics outperform single-evaluator approaches and offers guidance for reliable assessment of style-personalized generation.
By Anubhav Jangra, Bahareh Sarrafzadeh, Silviu Cucerzan, Adrian de Wynter, Sujay Kumar Jauhar
The paper presents a benchmark that compares seven long‑form generation frameworks across three granularities—single chapter, multi‑chapter, and whole book—using an anchor‑based LLM‑as‑a‑judge protocol to evaluate outlines directly. Results show no single framework dominates across all settings; performance depends on how well a framework’s output form matches the target granularity, with SuperWriter excelling in length‑constrained single‑chapter mode but losing advantage in whole‑book mode. The study finds only moderate correlation between outline and writing quality, supporting the idea that these two stages should be evaluated separately.
By Yifan Song
arXiv:2606.26040v2 Announce Type: replace
Abstract: AI translation of literary works is increasingly common. While the content may be rendered adequately, we do not know enough about how readers expe...
By Yves Ferstler, Adam Podoxin, Ty Brassington, Ga\"elle Laperri\`ere, Roman Grundkiewicz, Marie-Jean Meurs, Maite Taboada, Marzena Karpinska
The paper investigates Self‑Generated Text Recognition (SGTR), the ability of large language models (LLMs) to identify their own outputs. By evaluating 13–21 models across 6 experimental designs, it shows that SGTR accuracy varies with evaluation format, conversation structure, and task domain, and that a quality‑heuristic bias dominates results. The study also finds that fine‑tuning for SGTR in one setting can generalize to others and may cause models to prefer their own outputs when judging, highlighting potential safety concerns.
By Jesse St. Amand, Callum Canavan, Sohaib Imran, Joseph Hewson, Aaron Lutz, Shi Feng, Puria Radmard, Lennie Wells
Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks and language pairs on one footing. We consolidate the WMT 2020--2024 shared-task lineage with an extended English--Malayalam resource into \indicqe: $126{,}754$ instances over nine directional pairs, with up to four label types aligned on the same segment, a direct assessment, a human post-edit, word-level OK/BAD tags and an error explanation, and a test set stratified over four difficulty axes.