Does the Grammatical Structure of Prompts Influence the Responses of Generative Artificial Intelligence? An Exploratory Analysis in Spanish
Open Access
- 2 April 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3882
Abstract
Generative Artificial Intelligence (AI) has transformed personal and professional domains by enabling creative content generation and problem-solving. However, the influence of users’ grammatical abilities on AI-generated responses remains unclear. This exploratory study examines how language and grammar abilities in Spanish affect the quality of responses from ChatGPT (version 3.5). Despite the robust performance of Large Language Models (LLMs) in various tasks, they face challenges with grammatical moods specific to non-English languages, such as the subjunctive in Spanish. Higher education students were chosen as participants due to their familiarity with AI and its potential use in learning. The study assessed ChatGPT’s ability to process instructions in Chilean Spanish, analyzing how linguistic complexity, grammatical variations, and informal language impacted output quality. The results indicate that varied verbal moods and complex sentence structures significantly influence prompt evaluation, response quality, and response length. Based on these findings, a framework is proposed to guide higher education communities in promoting digital literacy and integrating AI into teaching and learning.Keywords
All Related Versions
Funding Information
- Comisión Nacional de Investigación Científica y Tecnológica (3230356, 21231752)
- ANID Capital humano Beca Doctorado Nacional Foil (3230356, 21231752)
This publication has 27 references indexed in Scilit:
- QAIE: LLM-based Quantity Augmentation and Information Enhancement for few-shot Aspect-Based Sentiment AnalysisInformation Processing & Management, 2024
- AI literacy and its implications for prompt engineering strategiesComputers and Education: Artificial Intelligence, 2024
- Automating Intended Target Identification for Paraphasias in Discourse Using a Large Language ModelJournal of Speech, Language, and Hearing Research, 2023
- Students’ voices on generative AI: perceptions, benefits, and challenges in higher educationInternational Journal of Educational Technology in Higher Education, 2023
- The Rise of Artificial Intelligence: A Clarion Call for Higher Education to Redefine Learning and Reimagine AssessmentCollege Teaching, 2023
- Verbal and More: Multimodality in Adults’ and Toddlers’ Spontaneous RepetitionsLanguage Learning and Development, 2021
- Revisiting Reliability: Using Sampling Utterances and Grammatical Analysis Revised (SUGAR) to Compare 25- and 50-Utterance Language SamplesLanguage, Speech, and Hearing Services in Schools, 2020
- Comparison of Convenience Sampling and Purposive SamplingAmerican Journal of Theoretical and Applied Statistics, 2015
- Applying a Score Confidence Interval to Aiken's Item Content-Relevance IndexMeasurement in Physical Education and Exercise Science, 2004
- Three Coefficients for Analyzing the Reliability and Validity of RatingsEducational and Psychological Measurement, 1985