Text Readability and Simplification Peer reviewed

Combining the fine-tuned GPT model and linguistic complexity indices in assessing second language (L2) Spanish writing

Pengzhan Yang, Wenqian Huang, Guangyuan Yao

Innovation in Language Learning and Teaching | Jul 14, 2026

Abstract

Automated Writing Evaluation (AWE) is increasingly leveraging Large Language Models (LLMs), but research on fine-tuned models for L2 Spanish and their relationship with linguistic complexity (LC) remains limited. This study evaluates three models for assessing a large corpus of L2 Spanish writing: (1) a fine-tuned Generative Pre-trained Transformer (GPT)-4.1 model, (2) a model using 87 LC indices, and (3) a hybrid model integrating both. Results demonstrate that the hybrid model achieved the highest reliability and accuracy (QWK = 0.93), significantly outperforming both the GPT model alone (QWK = 0.88) and the LC model (QWK = 0.83). The integration of LC indices particularly improved the accuracy for assessing Intermediate-level texts. These findings suggest a synergy where explicit linguistic features provide analytical precision that enhances the holistic judgments of the LLM. The study advocates for a hybrid approach to AWE that combines generative AI with linguistic analysis to create more accurate, valid, and interpretable assessment tools.

Direct answer

What can I do from this paper page?

Use this page to scan "Combining the fine-tuned GPT model and linguistic complexity indices in assessing second language (L2) Spanish writing" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Text Readability and Simplification research, save the paper, or map adjacent work.

Authors

Researchers on this paper

Pengzhan Yang

first | The University of Sydney | ORCID 0009-0005-7882-6616

Wenqian Huang

middle | The University of Sydney | ORCID 0009-0005-7631-8546

Guangyuan Yao

last | Central South University | ORCID 0009-0000-9123-1696

Research areas

Follow related topics

Latest Text Readability and Simplification research Latest Artificial Intelligence in Healthcare and Education research Latest Topic Modeling research

Citation

BibTeX

@article{Yang2026Combining,
  title = {Combining the fine-tuned GPT model and linguistic complexity indices in assessing second language (L2) Spanish writing},
  author = {Pengzhan Yang and Wenqian Huang and Guangyuan Yao},
  journal = {Innovation in Language Learning and Teaching},
  year = {2026},
  doi = {10.1080/17501229.2026.2701987},
  url = {https://doi.org/10.1080/17501229.2026.2701987}
}

FAQ

Using this paper in a discovery workflow

How do I find related work for this paper?

Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.

How can I keep up with new Text Readability and Simplification research papers?

Follow Text Readability and Simplification research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.

Can I cite this paper from this page?

This page includes a static BibTeX block for Combining the fine-tuned GPT model and linguistic complexity indices in assessing second language (L2) Spanish writing. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.

Follow this research in Scollr

Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.

Get the app