# “It is important to consult” a linguist: Verb-Argument Constructions in ChatGPT and human experts’ medical and financial advice

## TL;DR

This study compares language patterns in advice from humans and ChatGPT using verb-argument constructions, finding similarities and differences in how advice is structured.

## Contribution

The novel contribution is applying Usage-Based Construction Grammar to analyze AI-generated advice and track its evolution.

## Key findings

- ChatGPT relies more on frequent verb-argument constructions compared to human texts.
- Newer GPT models show more human-like verb patterns despite differences in macro-level text features.
- VAC analysis reveals meaningful differences in conveyed advice content between humans and AI.

## Abstract

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.