# Linguistic Characteristics of AI-Generated Text: A Survey arXiv: https://arxiv.org/abs/2510.05136 ยท HTML: https://mlsanity.com/paper/2510.05136/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 23 of its 59 references that are in the map. - First posted on arXiv 1 Oct 2025. ## Builds on (most cited first, 23 of 23) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023) - [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023) - [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024) - [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021) - [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023) - [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023) - [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024) - [Contrasting Linguistic Patterns in Human and LLM-Generated News Text](https://mlsanity.com/paper/2308.09067/) (2023) - [Do LLMs write like humans? Variation in grammatical and rhetorical styles](https://mlsanity.com/paper/2410.16107/) (2024) - [Detection and Measurement of Syntactic Templates in Generated Text](https://mlsanity.com/paper/2407.00211/) (2024) - [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023) - [Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions](https://mlsanity.com/paper/2308.02312/) (2023) - [A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism](https://mlsanity.com/paper/2401.05749/) (2024) - [Differentiate ChatGPT-generated and Human-written Medical Texts](https://mlsanity.com/paper/2304.11567/) (2023) - [Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG](https://mlsanity.com/paper/2406.13069/) (2024) - [Classification of Human- and AI-Generated Texts: Investigating Features for ChatGPT](https://mlsanity.com/paper/2308.05341/) (2023) - [Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis](https://mlsanity.com/paper/2304.05534/) (2023) - [Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text](https://mlsanity.com/paper/2309.07689/) (2023) - [Whose LLM is it Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard](https://mlsanity.com/paper/2402.14533/) (2024) - [Long-form analogies generated by chatGPT lack human-like psycholinguistic properties](https://mlsanity.com/paper/2306.04537/) (2023) - [PetKaz at SemEval-2024 Task 8: Can Linguistics Capture the Specifics of LLM-generated Text?](https://mlsanity.com/paper/2404.05483/) (2024) - [RFBES at SemEval-2024 Task 8: Investigating Syntactic and Semantic Features for Distinguishing AI-Generated and Human-Written Texts](https://mlsanity.com/paper/2402.14838/) (2024) ## Built on by (most cited first, 7 of 7) - [Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy](https://mlsanity.com/paper/2603.23146/) (2026) - [AI Text Detectors and the Misclassification of Slightly Polished Arabic Text](https://mlsanity.com/paper/2511.16690/) (2025) - [False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models](https://mlsanity.com/paper/2601.07885/) (2026) - [Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies](https://mlsanity.com/paper/2604.14111/) (2026) - [Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies](https://mlsanity.com/paper/2605.20602/) (2026) - [From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale](https://mlsanity.com/paper/2605.28826/) (2026) - [Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models](https://mlsanity.com/paper/2606.03165/) (2026) ## Abstract (arXiv) Large language models (LLMs) are solidifying their position in the modern world as effective tools for the automatic generation of text. Their use is quickly becoming commonplace in fields such as education, healthcare, and scientific research. There is a growing need to study the linguistic features present in AI-generated text, as the increasing presence of such texts has profound implications in various disciplines such as corpus linguistics, computational linguistics, and natural language processing. Many observations have already been made, however a broader synthesis of the findings made so far is required to provide a better understanding of the topic. The present survey paper aims to provide such a synthesis of extant research. We categorize the existing works along several dimensions, including the levels of linguistic description, the models included, the genres analyzed, the languages analyzed, and the approach to prompting. Additionally, the same scheme is used to present the findings made so far and expose the current trends followed by researchers. Among the most-often reported findings is the observation that AI-generated text is more likely to contain a more formal and impersonal style, signaled by the increased presence of nouns, determiners, and adpositions and the lower reliance on adjectives and adverbs. AI-generated text is also more likely to feature a lower lexical diversity, a smaller vocabulary size, and repetitive text. Current research, however, remains heavily concentrated on English data and mostly on text generated by the GPT model family, highlighting the need for broader cross-linguistic and cross-model investigation. In most cases authors also fail to address the issue of prompt sensitivity, leaving much room for future studies that employ multiple prompt wordings in the text generation phase.