AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not

• URL: http://arxiv.org/abs/2608.27855v1
• Date: Fri, 28 Aug 2026 02:58:58 GMT
• Title: AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not
• Abstract summary: Text generated by large language models (LLMs) has been shown to be stylometrically distinct from human-written text.<n>We show that AI generation leaves a consistent stylometric footprint''<n>We show that AI editing, however, does not reproduce the same footprint.
• Score: 8.711791966428427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text generated by large language models (LLMs) has been shown to be stylometrically distinct from human-written text \citep{andreDetectingAIAuthorship2023, shahDetectingUnmaskingAIGenerated2023, oparaStyloAIDistinguishingAIGenerated2024, soto2024fewshot, liLinguisticDifferencesAI2025, selviogluFeatureExtractionAnalysis2025}. But LLMs are increasingly used not only to generate text but also to edit human writing, and it is unclear whether the two leave the same trace. We show that AI generation leaves a consistent ``stylometric footprint'': a small subset of features, primarily entropy and lexical diversity, consistently separates AI-generated text from human writing across 8 LLMs and 5 domains, while the remaining features depend heavily on the domain and generator. AI editing, however, does not reproduce the same footprint. Relative to their human-written sources, AI-edited texts show only a small increase in lexical diversity and a decrease in entropy, rather than the joint increase that characterizes AI generation. Lexical density, which contributes little to generation, instead becomes the dominant editing-associated signal. Stylometric features therefore separate AI-edited text from AI-generated text but are substantially less effective at separating it from human-written text. Our results suggest that ``AI text'' is not a single phenomenon: generation and editing leave qualitatively different stylometric traces and should be studied separately.

Related papers

• Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection [49.41415417307568]
  OpAI-Bench is an operation-guided benchmark for studying progressive human-to-AI text transformation.<n>We show that AI-text detectability is governed not only by the proportion of AI-edited content, but also by edit operation, domain, and cumulative revision history.
  arXiv  Detail & Related papers  (2026-06-04T17:58:05Z)
• 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions [50.1119556361129]
  We systematically define various notions of AI-generated text and their characteristics.<n>AITDNA is a new benchmark of human-machine co-constructed texts.<n>We benchmark various machine-generated text detectors and find that they often only perform well for specific notions but not as broad detectors.
  arXiv  Detail & Related papers  (2026-06-03T14:05:14Z)
• EditLens: Quantifying the Extent of AI Editing in Text [23.457378805409714]
  We show that AI-edited text is distinguishable from human-written and AI-generated text.<n>We train a regression model that predicts the amount of AI editing present within a text.<n>Not only do we show that AI-edited text can be detected, but also that the degree of change made by AI to human writing can be detected.
  arXiv  Detail & Related papers  (2025-10-03T16:27:48Z)
• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  This study systematically evaluations twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset.<n>Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• Beyond checkmate: exploring the creative chokepoints in AI text [9.65404451340112]
  We study portraying the nuanced distinctions between human and AI texts across text segments (introduction, body, and conclusion)<n>Our findings provide fresh insights into human-AI text differences and pave the way for more effective and interpretable detection strategies.
  arXiv  Detail & Related papers  (2025-01-31T16:57:01Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Raidar: geneRative AI Detection viA Rewriting [42.477151044325595]
  Large language models (LLMs) are more likely to modify human-written text than AI-generated text when tasked with rewriting. We introduce a method to detect AI-generated content by prompting LLMs to rewrite text and calculating the editing distance of the output. Our results illustrate the unique imprint of machine-generated text through the lens of the machines themselves.
  arXiv  Detail & Related papers  (2024-01-23T18:57:53Z)
• Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts [22.852855047237153]
  We show that the average intrinsic dimensionality of fluent texts in a natural language is hovering around the value $9$ for several alphabet-based languages and around $7$ for Chinese. This property allows us to build a score-based artificial text detector.
  arXiv  Detail & Related papers  (2023-06-07T18:38:04Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Is This Abstract Generated by AI? A Research for the Gap between AI-generated Scientific Text and Human-written Scientific Text [13.438933219811188]
  We investigate the gap between scientific content generated by AI and written by humans. We find that there exists a writing style'' gap between AI-generated scientific text and human-written scientific text.
  arXiv  Detail & Related papers  (2023-01-24T04:23:20Z)
• How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN [63.79300884115027]
  Current language models can generate high-quality text. Are they simply copying text they have seen before, or have they learned generalizable linguistic abstractions? We introduce RAVEN, a suite of analyses for assessing the novelty of generated text.
  arXiv  Detail & Related papers  (2021-11-18T04:07:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.