Casal J Elliott, Stewart Christopher M, Windsor Alistair J
Department of English, University of Memphis, Memphis, Tennessee, United States of America.
Institute for Intelligent Systems, University of Memphis, Memphis, Tennessee, United States of America.
PLoS One. 2025 May 27;20(5):e0324611. doi: 10.1371/journal.pone.0324611. eCollection 2025.
This paper adopts a Usage-Based Construction Grammar perspective to compare human- and AI-generated language, focusing on Verb-Argument Constructions (VACs) as a lens for analysis. Specifically, we examine solicited advice texts in two domains-Finance and Medicine-produced by humans and ChatGPT across different GPT models (3.5, 4, and 4o) and interfaces (3.5 Web vs. 3.5 API). Our findings reveal broad consistency in the frequency and distribution of the most common VACs across human- and AI-generated texts, though ChatGPT exhibits a slightly higher reliance on the most frequent constructions. A closer examination of the verbs occupying these constructions uncovers significant differences in the meanings conveyed, with a notable growth away from human-like language production in macro level perspectives (e.g., length) and towards humanlike verb-VAC patterns with newer models. These results underscore the potential of VACs as a powerful tool for analyzing AI-generated language and tracking its evolution over time.
本文采用基于用法的构式语法视角来比较人类生成的语言和人工智能生成的语言，重点关注动词-论元结构（VACs）作为分析的视角。具体而言，我们研究了金融和医学这两个领域中由人类以及ChatGPT在不同GPT模型（3.5、4和4o）和接口（3.5网络版与3.5 API）下生成的征求意见文本。我们的研究结果表明，在人类生成的文本和人工智能生成的文本中，最常见的动词-论元结构的频率和分布具有广泛的一致性，不过ChatGPT对最频繁出现的结构的依赖程度略高。对占据这些结构的动词进行更仔细的研究发现，所传达的意义存在显著差异，从宏观层面（如长度）来看，人工智能生成语言越来越不像人类语言，而随着模型更新，在动词-论元结构模式上则越来越像人类语言。这些结果强调了动词-论元结构作为分析人工智能生成语言并追踪其随时间演变的有力工具的潜力。
